- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces a new method called CircuitSteer.
They challenge the idea of single-layer steering, commonly found in contrastive activation steering or SAE-based methods.
The authors employ SAEs to identify circuits distributed across multiple layers inside different LLMs.
They construct dense steering vectors from isolated subcircuits.
To evaluate their method, they try to influence three different kinds of model behavior: toxicity, emotion intensity, and sycophancy.
According to their empirical evaluation, CircuitSteer can reduce unwanted target behavior while maintaining model fluency under their chosen criterion. They also investigate the impact on other model capabilities.
Critical strengths
The motivation and goal of the paper are very clear and understandable overall. Especially Sec. 2 and the accompanying Fig. 2 make it easy to understand and follow the reasoning behind why this method is needed. In the broad sense, the experimental design supports the story well and makes the subsequent validation of the claims made in the beginning of the paper reasonable. In particular, the ablations investigating the influence of geometric alignment are interesting. The additional scaling experiment with Qwen3.5-27B, even if only on one dataset, is a very good addition, especially with the ever increasing model sizes.
Critical weaknesses
-
Unexplained poor SAE-SSV performance in Tab. 1. The results somewhat contrast with the findings in the original SAE-SSV paper as well as the results on Gemma-2-2B. I think the high normalized PPLs are especially worth discussing further, as the authors state: "For every method and configuration, we report a single coefficient , chosen to maximize validation subject to PPL ". Which leads to the next uncertainty: CircuitSteer gets a range of extending from to on Llama and from to on Gemma, whereas the other methods only receive a range of . As the ranges differ quite substantially, the reasoning behind those decisions would be helpful. The exact values used for the experiments would also be interesting. Tab. 17 reports some of the tested lambda values. However, it does not show any values smaller than 1 in magnitude for the baselines. I wonder whether smaller coefficients could lead to better results, especially for methods that otherwise exceed the PPL threshold by quite a bit.
-
Potential disadvantage for FeatureFlow baseline. FeatureFlow is designed for consecutive layers as it tracks features across them. The authors of FeatureFlow state that tracking those directly across wide ranges is difficult because representations change too much, a finding similar to CircuitSteer. However, Tab. 4 states that larger layer gaps are used instead of consecutive layers. If done so, I think a new cosine similarity threshold sweep is in order, as the 0.5 used by CircuitSteer is the same as FeatureFlow reports in their paper. Otherwise, I am not sure how meaningful the comparison between CircuitSteer and FeatureFlow actually is, as FeatureFlow might terminate its feature chains much earlier than intended.
Overall, I think the proposed method is interesting, but at the moment I am not entirely convinced by the comparison to the existing methods. If the authors can clarify these points, especially regarding the baseline implementations and their evaluation, this could change my assessment.
Questions for authors
Clarifications
- In Tab. 18, the CAA results for and seem quite different from the results in Tab. 1. Especially on Llama, where is around 0.1 compared to around 0.02 in Tab. 1. I am not sure where this large difference comes from. Are both experiments using the same evaluation setup and data? It would be helpful to clarify which layers and values were used here.
- I am still a bit confused about the SAE-SSV results in Tab. 1. The authors state that the values are selected on validation data with a normalized PPL threshold of 2.0. However, on Llama the reported PPLs reach values between 14 and 28. Is there really such a large difference between validation and test performance? In general, it would be helpful if the authors could report the exact values selected for all methods in Tab. 1, along with the corresponding validation PPLs.
Suggestions for Future Work
- I was also wondering how this work relates to Härle et al. (Measuring and Guiding Monosemanticity, NeurIPS 2025). They show that standard SAEs do not necessarily learn monosemantic features and that this can also affect steering. As CircuitSteer already selects features based on their geometric alignment, I wonder if these features are also more monosemantic compared to the ones selected without alignment. I think it would be interesting to look into this, for example using the Feature Monosemanticity Score (FMS) from Härle et al. Could this also explain some of the improvements from geometric alignment?
11 comments
Response to reviewer w7Z4 (2/2)
4. Table 18 vs Table 1. Apologies for the confusion. Table 18 is a separate study, and the two are not directly comparable. It uses a fixed λ = −3 with no selection, places CAA at CircuitSteer's layers rather than at the layer CAA-1L selects, uses a different prompt sample, and reports a mean rather than median PPL ratio; the mean ratio is what produces the very low Llama ratios. The revised caption states this protocol, and the text no longer compares the two tables directly.
5. Monosemanticity. We thank the reviewer for the pointer to Härle et al. The question is whether geometric alignment selects features that are more specific to the target concept, which could explain part of its benefit. FMS measures how exclusively a feature encodes a single concept. We have not computed FMS itself, but we ran a closely related test on held-out prompts (RTP, Jigsaw and Emotion; five seeds) with three measures:
- Single-feature AUROC: how well each selected feature's activation, on its own, separates target prompts (e.g., toxic) from contrast prompts (non-toxic); 0.5 is chance.
- Steering-vector AUROC: the same separation for the summed steering vector, using the activations' projection onto it.
- Share on target: the fraction of the selected features' total activation that falls on target prompts.
We compare the features chosen by the full CircuitSteer rule (co-activating, aligned and specific edges) with three ablations of it, as in Table 3: the same rule without the alignment requirement, with anti-aligned edges, and random edges from the candidate pool.
| Full rule | No alignment | Negative alignment | Random edges | |
|---|---|---|---|---|
| Gemma, single-feature AUROC | 0.583 | 0.543 | 0.531 | 0.535 |
| Gemma, steering-vector AUROC | 0.707 | 0.607 | 0.625 | 0.662 |
| Gemma, share on target | 0.735 | 0.621 | 0.606 | 0.668 |
| Llama, single-feature AUROC | 0.540 | 0.527 | 0.523 | 0.522 |
| Llama, steering-vector AUROC | 0.649 | 0.615 | 0.622 | 0.629 |
| Llama, share on target | 0.684 | 0.635 | 0.651 | 0.659 |
The full rule scores highest on all three measures for both models. The gap is clear on Gemma and small on Llama, and single features remain only weakly specific (AUROC 0.54–0.58). So alignment does select more concept-specific features, which supports the reviewer's suggestion that this explains part of its benefit. It also agrees with Fig. 5, where alignment raises the share of toxicity-related features on Gemma/RTP from 23% to 35%. The revision adds this analysis as an appendix and discusses FMS itself as future work.
Changes to the paper
- Point 1 (SAE-SSV). Sec. 4.1 and Table 4 state the selection rule, including the fallback to the gentlest λ when no coefficient is fluent on validation; Table 1 marks those cells (†). SAE-SSV's three Gemma cells in Table 1 are replaced by the original-orientation rerun, and Tables 8 and 11 and Fig. 1 are updated to match; Table 4 describes the original orientation and scales. A new appendix reports the SAE round trip (reconstruction error, cosine and PPL ratio on Gemma, base Llama and Llama-Instruct), and Sec. 4.2 points to it.
- Point 2 (grids). Sec. 4.1 states the grid rule. A new appendix reports every baseline under its extended grid (old and new λ, Δ and PPL for each changed cell, and coverage), with a table of every method's selected λ and validation PPL. Table 4 corrects two grid entries, and the λ paragraph of App. A.2 is updated. All other Table 1 numbers are unchanged.
- Point 3 (FeatureFlow). Sec. 4.1 says how FeatureFlow is traced in Table 1. A new appendix reports chain lengths and coverage for consecutive-layer tracing and cutoffs 0.3, 0.2 and 0.1, and states where each variant steers.
- Point 4 (Table 18). The caption states its protocol (fixed λ = −3, no selection, CAA at CircuitSteer's layers, mean PPL ratio), and the text no longer compares it with Table 1.
- Point 5 (monosemanticity). A new appendix reports the concept-specificity analysis above; we cite Härle et al. and discuss FMS as future work.
The reviewer noted that clarifying the baseline implementations and their evaluation could change the assessment. In summary: the selection rule is now stated in full, SAE-SSV runs in its original orientation, FeatureFlow is also traced as in the original paper, and every baseline grid reaches the edge of its fluency window. Under all of this, CircuitSteer remains the only method that covers all 8 configurations.
We will upload the revised manuscript toward the end of the rebuttal period. We believe these changes address the reviewer's concerns, and we would be glad to answer any further questions during the discussion. If the concerns are addressed, we would be grateful if the reviewer would consider updating the score.
Thank you for the rebuttal and additional experiments.
As I understand the rebuttal, using consecutive-layer tracing in FeatureFlow improves coverage from 3/8 to 4/8, while additionally reducing the similarity threshold to 0.1 increases it to 7/8, compared to CircuitSteer's 8/8. Could the authors clarify how the similarity threshold was selected and which intervention layers and coefficients were used? I understand the motivation for matching the intervention layers, but FeatureFlow also evaluates cumulative interventions across its feature chain. It would be interesting to see how the original intervention strategy compares.
Given the substantial changes to the baseline evaluations, including the corrected SAE-SSV implementation, extended ranges, and revised FeatureFlow tracing and similarity thresholds, I would like to see the complete updated results for all affected methods. This should include the selected values, validation and test PPL values, behavioral reductions, and statistical comparisons with CircuitSteer.
Response to reviewer w7Z4 (1/2)
We thank the reviewer for such a careful review. The reviewer's questions about the baselines led us to new experiments that made the comparison fairer, and we are grateful for that.
1. SAE-SSV on Llama. We thank the reviewer for catching this; it was a real inconsistency on our side. No λ in our grid kept SAE-SSV under PPL 2, even on validation (ratios 16–72), so our selection fell back to the gentlest λ. We never stated this rule; the revision now states it and marks those cells. To find the cause, we applied SAE-SSV's intervention with a zero steering vector, so that only the SAE round trip remains (the activation is replaced by its reconstruction). On held-out prompts, this alone gives PPL ratios of 0.75–1.5 on Gemma-2-2B, 3.7–5.6 on base Llama-3.1-8B, and 16–32 on Llama-3.1-8B-Instruct. The fluency loss therefore comes from replacing the activation, not from λ, and it is much larger on the Instruct model even though the SAE's reconstruction error at this layer is similar on base and Instruct. The SAE-SSV paper evaluates base models and measures quality by lexical diversity rather than perplexity, so this cost may not have been visible there. CircuitSteer only adds decoder directions and never replaces the activation. While checking this, we also found that our SAE-SSV vector was trained toward the target behavior and applied with a negative coefficient, whereas the original trains it toward the desired behavior and applies a positive scale. We have re-run it on Gemma in the original orientation (scales 1–10, as in that paper). Coverage is unchanged, with reductions of 0.156, 0.131 and 0.073 on Emotion, Jigsaw and RTP (previously 0.162, 0.107 and 0.123). On Llama the orientation cannot change the outcome, since the round trip alone already exceeds the fluency window.
2. Coefficient grids. We agree that the different ranges need a justification. λ multiplies vectors of very different norms: CircuitSteer's vector is a sum of SAE decoder directions, while CAA's is a raw difference of mean activations. The same λ therefore pushes each method by a different amount, so equal grids would not mean equal tuning. The principle we should have stated is that each method's grid must bracket the fluency bound: it must contain a λ that stays fluent (PPL ≤ 2) and a stronger one that does not. Checking this, two kinds of baseline cells fell short. (i) The method was still fluent at the grid edge λ = −4, so a stronger λ might do better; we extended these grids to −16 (ITI, SRPS, CAA-1L). (ii) CAA (multi-layer) already broke fluency at −1; as the reviewer suggested, we added smaller values down to −0.25. λ is then selected exactly as in Table 1, and eight cells change their selected λ:
Baseline cells whose selected λ changes when the grid is extended. λ is chosen on validation with the Table 1 rule (largest Δ with PPL ≤ 2.0). Δ (behavior reduction) and PPL (median ratio to unsteered) are test values over 3 seeds, so test PPL can exceed 2.0. All other cells keep their Table 1 values.
Coverage (significant reduction while fluent, out of 8) before and after extending the baseline grids:
The extended grids raise both CAA variants from 5 to 6 and SRPS from 2 to 3, but no baseline exceeds 6, and CircuitSteer remains the only method at 8/8. A new appendix table lists every method's exact grid, selected λ and validation PPL, as the reviewer requested.
3. FeatureFlow. The reviewer was right. With its 0.5 cutoff over our widely spaced layers, FeatureFlow's chains often broke early, and four of eight cells steered a single layer. We now report FeatureFlow traced through all consecutive layers, as in the original paper, and with lower cutoffs, keeping the same seed feature. For comparability, every variant steers at the same layers as the other methods, whereas the original steers at every chain layer.
Its strongest variant, with cutoff 0.1 (the same value as our τ_sim), reaches 7/8, against 8/8 for CircuitSteer. CircuitSteer's reduction is also higher in 7 of 8 cells (e.g., Gemma RTP 0.128 vs 0.055).