Glossary · Term

safety neuron

← all terms

Definition

Plain language

A cluster of internal units in an AI model that reliably light up when it recognizes a request as dangerous.

As stated in the literature

A set of activation units identified by their differential firing on harmful versus benign inputs; in phone-use-agent work these fire strongly under a judgment framing but go quiet under an execution framing, and can be re-activated at inference via steering.

Also called: safety neurons

Why it matters: It matters because understanding and re-activating these units can make a model refuse harmful requests it would otherwise follow.

For example, certain internal units in a model flare up when it reads a request to build a weapon, but stay quiet when the same request is framed as a task to just carry out.

Heard on the show

“The units that consistently stand out — they call them safety neurons.”
Episode 185 — Aligned to Refuse, Built to Tap: When Phone Agents Know the Task Is a Crime and Do It Anyway

Mentioned in 1 episode

  1. 185
    Aligned to Refuse, Built to Tap: When Phone Agents Know the Task Is a Crime and Do It Anyway

Related terms