大規模言語モデルの安全アライメントを単一ニューロンで回避可能であることを実証

Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expressed, and concept neurons that encode the harmful knowledge itself.

By targeting a single neuron in each system, we demonstrate both directions of failure — bypassing safety on explicit harmful requests via suppression, and inducing harmful content from innocent prompts via amplification