Researchers explored design choices for activation probes in detecting language model deception
Researchers explored how design choices for activation probes interact when detecting and steering deception, high-stakes awareness and sycophancy in a language model.
The layer that steers a behaviour best can be located well before the layer that detects it best.
Sources behind this report
- arXiv
Research · abstract · CC0 1.0
Research manuscript in arXiv. Peer-review status is not recorded here; consult the linked version and publication.
Source published
Read by the newsroom
Report history
No earlier revision dates are retained here. This does not establish that the report has never changed; read any dated updates and corrections.
This brief was made by AI and checked against its cited public sources. How the newsroom works