Revision History
Activation steering · 10 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected a composite ActAdd quote; wrong authors and years for REMEDI, In-Context Vectors, the sycophancy post, Steering Awareness and the collateral-damage paper; misstated findings of the Tan et al. reliability paper, Anthropic's feature-steering bias study, the sentiment-direction paper, the refusal-direction paper and the sycophancy post (base model, not chat; no capability numbers); a false 'first' claim; and DeepMind credit for academic and Microsoft work (plus 15 minor fixes)
Version 10 · Nov 5, 2026, 12:43 PM
- Correction: Goodfire deprecated its SAE demo interface and API in February 2026
Version 9 · Oct 27, 2026, 10:35 AM
- Update: Ember described in the past tense (public API deprecated February 2026); link to canonical goodfire_ai
Version 8 · Oct 27, 2026, 06:15 AM
- Correction: Goodfire's Ember supported Llama 3.1 8B and Llama 3.3 70B; it did not offer steering on Claude models.
Version 7 · Oct 27, 2026, 06:15 AM
- Improve internal links (2026-10-13)
Version 6 · Oct 13, 2026, 10:03 AM