研究人员开发了一种新的无监督方法，通过对齐语义内容和内部计算机制来发现大型语言模型中的特征。该方法根据模型输出的含义及其潜在的归因签名对其进行聚类，而无需预定义的输出目标。发现的聚类揭示了传统方法可能忽略的多种延续模式，为审计大型语言模型的内部工作提供了一种可扩展的方法。 AI
影响 提供了一种审计大型语言模型内部计算的新颖方法，增强了模型的安全性和可解释性。
排序理由 该集群包含一篇详细介绍新研究方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.08236v1 Announce Type: cross Abstract: As large language models are increasingly deployed in high-stakes settings, there is a growing need for tools that audit not only model outputs but also the internal computations that produce them. Circuit analysis is a central ap…
As large language models are increasingly deployed in high-stakes settings, there is a growing need for tools that audit not only model outputs but also the internal computations that produce them. Circuit analysis is a central approach in mechanistic interpretability, but it is …