Mech interp tutorial drops tomorrow: steering LMs, abliteration, and monosemantic neurons hands-on
CatAstro_Piyush · x · 2026-11-01
A mech interp practitioner announced a hands-on tutorial video on steering language models, covering: finding feature directions in the residual stream, model uncensoring and abliteration, locating monosemantic neurons, and auto-interpretability. The attached graphic demonstrates the "tomato neuron" — a single layer-7 neuron that consistently activates tomato-related outputs across diverse prompts.
More from Research
- awesome-ai-constitutions repo collects AI constitutions & model specs with generalization research — dhadfieldmenell · 2026-11-01
- Karpathy's nanochat hits 59K stars: a full LLM training lab in one repo — techNmak · 2026-11-01
- Same 2.4 eV band gap, different routes: SHAP explains per-prediction feature contributions — bravo_abad · 2026-11-01
- Hands-on tutorial trains a decision model on Qwen3-0.6B from scratch — dl_weekly · 2026-11-01
- From-scratch 8M-parameter LLM: dev blogs the whole training journey — the-random-guy-2002 · 2026-11-01
- Fine-grained MoE is the easiest win: DeepSeek-V3-style 128 experts cut loss by up to 6.2% — ivan_bezdomny · 2026-11-01