RACE模型评估LLM神经元功能一致性，计算效率高，值得了解。
RACE（残差对齐一致性估计）是一种前向传递的统计框架，用于评估Transformer神经元在域范围内的功能一致性。实验表明，RACE在域特异性方面优于基于梯度的点估计，且计算开销比梯度方法低两个数量级。
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 estimates. Meanwhile, token-distribution-level results verify the association between the selected neurons and the target domain. Furthermore, its computational overhead is two orders of magnitude lower than that of gradient-based methods.