Proposal: 'behavior heritability' — the causal share of a neuron's correlation with LLM behavior
Sauers_ · x · 2026-10-16
A concept proposal for LLM interpretability: behavior heritability — the percentage of a neuron's neuron↔behavior correlation driven by that neuron's causal effects. It can be measured by intervening on the neuron versus looking at correlation left unexplained by causal direct effects, separating genuine causal contribution from mere correlation. An idea sketch, with no paper or experiments attached yet.
More from Research
- Lean v4.35.0 ships verified kernels — one written and proven consistent by Claude — geoffreyirving · 2026-10-16
- MP-Bench: 12 voice agents no better than coin flip at knowing when to speak in group chats — solyarisoftware · 2026-10-16
- Neuron-level GWAS + PheWAS on Qwen3-8B pinpoints safety-critical neurons — Sauers_ · 2026-10-16
- Tencent squeezes 770B-parameter Hunyuan Hy4 Preview into 214 GiB at ~2.38 bits per weight — coolmum18 · 2026-10-16
- 200 chess games suggest in-context learning doesn't work yet, experimenter says — akbirthko · 2026-10-16
- Mosaic: multi-session agentic RL with hierarchical advantage estimation — LARK-Lab · 2026-10-16