contrastive-neuron-attribution

Tag

Cards List
#contrastive-neuron-attribution

@NousResearch: Today we release Contrastive Neuron Attribution (CNA), a method for steering LLM behavior by identifying and ablating s…

X AI KOLs Following · 2026-05-19 Cached

NousResearch releases Contrastive Neuron Attribution (CNA), a method to steer LLM behavior by ablating sparse MLP circuits without training autoencoders or degrading benchmarks, validated on refusal circuits across models up to 70B parameters.

0 favorites 0 likes
#contrastive-neuron-attribution

Targeted Neuron Modulation via Contrastive Pair Search

Hugging Face Daily Papers · 2026-05-12 Cached

Contrastive neuron attribution (CNA) identifies a sparse set of MLP neurons that distinguish harmful from benign prompts, enabling effective behavioral steering in instruction-tuned LLMs without degrading output quality. The method reduces refusal rates by over 50% on jailbreak benchmarks while preserving fluency.

0 favorites 0 likes
← Back to home

Submit Feedback