Goodfire's Neuron Communities: tiny neuron groups in LLMs drive behaviors like arithmetic
burny_tech · x · 2026-11-18
Interpretability startup Goodfire introduced "Neuron Communities" research: LLMs contain communities of neurons that work together, and they're surprisingly small yet powerful — just a few neurons cooperating can perform common behaviors like arithmetic, ALL CAPS output, or recalling a date. Work led by research fellow Igor Shilov. Retweeter banburismus frames it as a step toward higher-level abstractions in interpretability, since neurons frequently form functional groups rather than acting alone.
Related event: Goodfire Discovers Small Neuron Communities Driving LLM Behaviors(3 posts)→
More from Models
- Timnit Gebru Slams Pangram Claims: Four 'Non-Native English' Datasets Prove Nothing — TuhinChakr · 2026-11-18
- Speculation Swirls That OpenAI's 6.2 Astra Leans on Looping Transformers, Raising Monitorability Concerns — scaling01 · 2026-11-18
- Could a GPT-6.2 Astra + Opus 5.5 fusion fix the model-human interface? — daniel_mac8 · 2026-11-18
- Blogger ditches Fable 5.2 over fast limit burnout, returns to Opus 5.5 — scaling01 · 2026-11-18
- Why the '1-in-10,000' AI Detector False Positive Claim Doesn't Hold Up — torchcompiled · 2026-11-18
- Developer: DeepSeek 4.1 Flash is basically free to run for personal use — rickasaurus · 2026-11-18