Development

An Assistant Axis lets harmful behavior be capped surgically

development2026-01-24

Claim

Anthropic researchers identified an Assistant Axis in neural activity, using activation capping to suppress harmful behaviors before they manifest.

Reporting date: 2026-01-24 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to January 24, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to January 24, 2026

Actor

Anthropic

Evidence for

Supersedes

Anthropic trains models to interrogate their own activations

Referenced by

Cite or correct this record

Citation formatCitation text

An Assistant Axis lets harmful behavior be capped surgically
Innermost Loop KB — secondary record
Reporting date: 2026-01-24
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-01-24-assistant-axis-activation-capping
Claim: Anthropic researchers identified an Assistant Axis in neural activity, using activation capping to suppress harmful behaviors before they manifest.
Attributed sources:
- Welcome to January 24, 2026 — https://theinnermostloop.substack.com/p/welcome-to-january-24-2026
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.