arXiv AI
Localization Does Not Imply Steerability: A Mechanistic Study of Sign Errors in LLM Mathematics
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 23
Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs
arXiv:2609.25602v1 Announce Type: new Abstract: In language models, the choice between believing the prompt and believing the weights is made by a handful of identifiable attention heads. Instruction...
arXiv Machine Learning
Aug 13
Orientation, not magnitude: the causal structure of task-vector interference in merged language models
arXiv:2608. 11797v1 Announce Type: new Abstract: Model merging by task arithmetic works until it doesn't, and the field diagnoses why with magnitudes: layerwise representation bias, deviations from cross-task linearity, parameter overlap.
arXiv Machine Learning
Aug 5
Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scaling
arXiv:2608. 03842v1 Announce Type: cross Abstract: When a language model fails on surface-perturbed input (typos, OCR noise, homophones), "which layer is responsible" has three natural operationalizations: where representations diverge most (sensitivity), where restoring clean activations recovers the prediction (causality), and where a small adapter can repair the damage (compensatory capacity) - and we show these three layer maps dissociate.
arXiv AI
Aug 11
Decided Upstream, Written Late: Locating and Pricing the Cross-Lingual Refusal Circuit of a Multilingual MoE
arXiv:2608. 08032v1 Announce Type: new Abstract: Safety alignment in multilingual models is uneven: a model that reliably refuses a harmful request in English will often comply with the same request in a lower-resource language.
arXiv Machine Learning
Jun 25
Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models
arXiv:2606. 24952v1 Announce Type: cross Abstract: A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should be able to modify it.
arXiv Machine Learning
Aug 13
Located but Not Releasable: Silent Gate Inversion and Bounded Linear Release
arXiv:2608. 11822v1 Announce Type: cross Abstract: A growing body of work reports that language models represent task-relevant latent structure that they fail to use.