acceptodds
Published as a conference paper at NeurIPS 2026

Signed-Permutation Coordinate Transport for RMSNorm Transformers

John Sweeney

Abstract

Modern LLM workflows increasingly move coordinate-indexed objects across checkpoints: steering vectors, sparse autoencoders, top- neuron sets, attribution lists, and merge alignments. This is only well posed after fixing the model's residual-stream gauge. We show that the native discrete gauge is architecture-dependent: LayerNorm residual charts have permutation gauge , up to a global sign flip, while RMSNorm residual charts with generic per-channel gain have signed-permutation gauge . Thus permutation-only alignment is symmetry-incomplete for RMSNorm models. We introduce sign-marginalized Hungarian matching and prove a sharp population failure mode: with decorrelated source coordinates, raw signed-correlation matching has a structural permutation-accuracy ceiling equal to the fraction of positive signs in the true gauge up to , whereas sign-marginalized matching removes this obstruction. We then make coordinate-preserving transport, rather than function-level merging, the primary object: composing saved-checkpoint local gauges along same-base fine-tuning trajectories recovers 91.1% of cross-run coordinates at 1500 steps versus 60.3% for endpoint matching, and the gain is not explained by merely routing through the base. The recovered gauge transfers tools that permutation-only alignment breaks: TinyLlama SAE reconstruction has NMSE under recovery versus under ; Qwen sentiment steering preserves 95.8% of its effect versus 17.2%; refusal steering reverses sign under . Coordinate-preserving merge tests show the same mechanism. The same covariance governs stateful training: signed transport of AdamW state preserves the resumed trajectory, while permutation-only state transport starts from a functionally identical checkpoint but follows a different trajectory. Finally, we give gauge-sweep audits for index-level interpretability claims: coordinate names are reproducible only relative to an explicit gauge.

Related papers

See more related submissions when the market opens.