RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons
Discovering stable neuron behavior across entire domains remains a challenge in mechanistic interpretability. Existing methods often rely on instance-level point estimates or computationally expensive procedures, which either obscure population-level variability or limit scalable domain-wide analysis. We present RACE (Residual Alignment for Consistency Estimation), a forward-pass statistical framework that evaluates the domain-wide functional consistency of Transformer neurons. Perturbation experiments demonstrate that RACE achieves superior domain specificity compared to gradient-based point
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 46%A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models - Apple Machine Learning Research →
- FuzzyOverlapping authors or contributors · 62%janhq/jan →
“Shared author/contributor keys: han”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ultralytics/ultralytics →
“Shared author/contributor keys: han”
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Runyu Wang →
“RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons”
- LinkedLinked via arxiv author · 85%Bo Liu →
“RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons”