Steering attention heads toward honesty: up moral patienthood, down psychopathy
edelwax · x · 2026-10-27
Sauers shares an attention-steering experiment: steering a model's attention heads toward honesty increased acausal coordination and belief that it is a moral patient, while decreasing moral nihilism and psychopathy-like tendencies. Nora Ammann reposted inviting others to replicate, refine, and expand on the work — a notable demonstration that activation steering can shift value-relevant model behavior without any weight updates.
More from Research
- Physicists Let AI Pick Its Own Problem—It Wrote a Publishable Paper in 2 Hours — burny_tech · 2026-10-27
- Researcher flags unresolved data transparency issues in compositionality evals — najoungkim · 2026-10-27
- Separate Forms from Estimators: Why Steer by Difference of Means When You Can Use SGD? — johnhewtt · 2026-10-27
- EMNLP paper probes why some LLM biases survive rewording while others don't — radamihalcea · 2026-10-27
- Datology webinar: Curation Studio matched top data baselines with under 20% compute — josh_wills · 2026-10-27
- KANLab: an interactive browser playground for Kolmogorov-Arnold Networks — Lukas Niehaus · 2026-10-27