Anthropic traces planning, hidden goals and jailbreak circuits in Claude 3.5 Haiku
Anthropic's circuit-tracing work found forward planning, multilingual abstractions, fabricated reasoning, jailbreak dynamics and a controlled hidden-goal mechanism inside Claude 3.5 Haiku. The team later released the tracing tools for open-weight models and an interactive public interface.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why it moved the index
The research exposed alignment-relevant mechanisms in a production model, tested causal interventions and was followed by a dated release of open-source circuit-tracing tooling. The authors state that useful explanations covered only about one quarter of attempted prompts, limiting assurance.
Assessment history
- R1Away 42 · confidence 92
Adds a missing Chris Olah-authored production-model interpretability result whose practical impact is verified by the subsequent public tool release.
14 Aug 2026