发表机构
NVIDIA Research; University of Wisconsin–Madison（英伟达研究院; 威斯康星大学麦迪逊分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出经验契约测试，区分LLM中特征引导与机制，发现跟踪概念和引导行为不足以证明模型使用该特征，结论依赖具体干预方式。
AI 中文摘要
在大型语言模型中，内部特征通常被解释为机制，当它们跟踪一个概念且其操纵能改变相关行为时。然而，引导可以将特征推离其自然范围，此时其效果未必反映模型自身的计算。我们审视这一推断，并提出一个经验契约，其测试在自然输入上观察到的特征值处进行评估。一项测试将特征值从表现出某行为的输入复制到匹配的未表现出该行为的输入（安装），或反向操作（移除）；另一项测试在上游编辑后恢复特征（下游救援）。安装衡量特征对该行为的充分性程度；移除和下游救援衡量模型对该特征的使用程度。应用于三类表示时，这两种强度显著分离。已发布的未知实体潜在特征强烈引导知识弃权（不执行），然而将任一已发布潜在特征中观察到的值安装到匹配提示中，仅转移了自然已知-未知弃权（不执行）对比的一小部分。密集的已知-未知方向在Gemma和Llama中显示出安装与移除之间的相反不对称性，且一个已发布的主题-动词一致特征集在多大程度上复现并恢复行为，取决于其值如何写入模型。因此，跟踪概念和引导行为本身并不表明模型使用了该特征，且每个结论仅适用于所测试的干预。
英文摘要
Internal features in LLMs are often interpreted as mechanisms when they track a concept and their manipulation changes a related behavior. Yet steering can push a feature far outside its natural range, where its effects need not reflect the model's own computation. We examine this inference and propose an empirical contract whose tests evaluate features at values observed on natural inputs. One test copies a feature's value from an input that shows a behavior into a matched input that does not (installation) or the reverse (removal); the other restores the feature after an upstream edit (downstream rescue). Installation measures how far the feature suffices for the behavior; removal and downstream rescue measure how much the model uses it. Applied to three kinds of representations, the two strengths separate sharply. The published unknown-entity latent strongly steers knowledge abstention, yet installing observed values from either published latent into matched prompts transfers only a small fraction of the natural known--unknown abstention contrast. Dense known--unknown directions show opposite asymmetries between installation and removal in Gemma and Llama, and how fully a released subject--verb agreement feature set reproduces and restores the behavior depends on how its values are written into the model. Tracking a concept and steering a behavior therefore do not by themselves show that the model uses a feature, and each conclusion holds only for the intervention tested.
