Deception Detection Probes

Evals

Tool (not an eval — tooling/reference entry)

Linear probes for strategic deception.

Category
Deception, scheming & alignment auditing
Insurance exposure
Model failure
Publisher
Apollo Research
Publisher type
Nonprofit / research org
License
unknown
Status
Stale (>12mo)
Last commit
2025-02-11
Stars
58

View source on GitHub →

Wanich Risk Lab, 2026.