Tag
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.
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.