- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This work adopts J-Lens loudness to identify useful layers and token positions for probing LLM activations without training probes. Experiments on two LLMs in grid-world tasks show that higher loudness is generally associated with better decoding accuracy for movement directions.
Critical strengths
- The idea is simple and interesting.
- The experimental results seems encouraging.
Critical weaknesses
- My main concen is that this work does not directly verify whether the selected layers achieve the best probing accuracy, which weakens one of its main claims.
- The experiments are limited to one environment and mainly one successful signal, so the generality of the method remains unclear.
Questions for authors
- Please add at least one experiment to demonstrate the optimality of the selected layers.
- Please consider more environments and signal types.
2 comments
Thank you again for your review. We've uploaded the revised PDF, and the general comment above lists everything that changed.
Optimality of the selected layers: We ran the experiment you asked for: probes at every layer of both models (Section 4.1, Figure 3, with full tables in Appendix C.8). For Qwen the loudest layer is also the best one. For GPT-OSS it sits on the high-accuracy plateau, two layers from the best. Therefore, we have softened the claim throughout the paper to "a layer on the plateau" rather than "the optimal layer", and we now present position selection as the main contribution.
More environments and signals: We added a second probing task whose labels come from the environment rather than from the model (Section 4.5), and loudness predicts decodability there as well. We couldn't add new environments in this cycle, and we state that as a main limitation.
Aside from the request for additional environments/signals, do these changes settle your concerns?
We thank the reviewer for the time spent on reviewing our paper submission, and for the concise summary of flaws. We added a general comment aimed to reply to all concerns raised by all reviewers, and we will reference it here while addressing your concerns.
Optimality of the selected layer. As stated in the general reply, we agree this was a potential over-claim. We tested it by running a sweep and find that, in short, the loudest layer is also the most decodable for Qwen3.6-35B-A3B and close to the most decodable for GPT-OSS-20B. It is near-optimal, not optimal, and we will revise the claim to match these results.
More environments and signals. Further signals and environments are unfortunately not feasible in this reviews cycle. To make up for this, we will add a second probing task with labels from the environment rather than labels verbalized by the model (experiment A). We will state this limitation in the paper, and treat our work as a first step towards understanding how to better select token positions for probing.
Would reducing the layer-selection claim resolve your main concern? And is there something else you would consider necessary for acceptance? Looking forward to your reply!