Limitations of This Steering Method
simi_97k · x · 2026-07-12
The author explains the limitations of this method:
- It requires a trained SAE for the target model;
- Steering vectors are customized per layer and per model;
- It is currently difficult to automatically find the optimal steering strength for each prompt during inference.
Related event: Limitations and Tooling for Cultural Steering Methods(2 posts)→
More from Research
- Navier-Stokes, Riemann, P vs NP: what this week's math buzzwords mean for you — koltregaskes · 2026-09-11
- Fruit fly connectome LLM weights land on Hugging Face, transformers-compatible — ngxson · 2026-09-11
- Fruit fly brain as an LLM: connectome-driven language model demo goes live — ngxson · 2026-09-11
- Harry Collins: LLMs can't do frontier science because they can't invent new language — whoamisri · 2026-09-11
- The Waymo effect: how AI is quietly making research less collaborative — JohnHammersley · 2026-09-11
- Causal-only attention for non-generative tasks is wasteful, argues HF engineer — antoine_chaffin · 2026-09-11