Using psychological constructs such as the Big Five, large language models (LLMs) can imitate specific personality profiles and predict a user's personality. While LLMs can exhibit behaviors consistent with these constructs, it remains unclear where and how they are represented inside the model and how they relate to behavioral outputs. To address this gap, we focus on questionnaire-operationalized Big Five concepts, analyze the formation and localization of their internal representations, and use interventions to examine how these representations relate to behavioral outputs. In our experiment, we first use probing to examine where Big Five information emerges across model depth. We then identify neurons that respond selectively to each Big Five concept and test whether enhancing or suppressing their activations can bias latent representations and label generation in intended directions. We find that Big Five information becomes rapidly decodable in early layers and remains detectable through the final layers, while concept-selective neurons are most prevalent in mid layers and exhibit limited overlap across domains. Interventions on these neurons consistently shift probe readouts toward targeted concepts, with targeted success rates exceeding 0.8 for some concepts, indicating that the model's internal separation of Big Five personality traits can be causally steered. At the label-generation level, the same interventions often bias generated label distributions in the intended directions, but the effects are weaker, more concept-dependent, and often accompanied by cross-trait spillover, indicating that comparable control over generated labels is difficult even with interventions on a large fraction of concept-selective neurons. Overall, our findings reveal a gap between representational control and behavioral control in LLMs.

翻译：利用大五人格等心理构念，大语言模型（LLMs）能够模拟特定人格特征并预测用户个性。尽管LLMs能表现出与这些构念一致的行为，但其在模型内部的表征位置、形成方式以及与行为输出的关联仍不明确。为填补这一空白，本研究聚焦于基于问卷操作化的大五人格概念，分析其内部表征的形成与定位，并通过干预实验探究这些表征与行为输出之间的关系。实验首先采用探测法检验大五人格信息在模型不同深度层中的涌现位置，继而识别对各人格概念具有选择性响应的神经元，并测试增强或抑制其激活能否使潜在表征与标签生成沿预期方向偏移。研究发现：大五人格信息在浅层即可快速解码，并持续至深层被检测到；概念选择性神经元多集中于中层，且不同人格域之间重叠有限。对这些神经元进行干预能持续将探测器的读取结果向目标概念偏移——部分概念的定向成功率超过0.8，表明模型内部对大五人格特质的表征具有可因果调控性。在标签生成层面，相同干预通常能使生成标签分布向预期方向偏移，但效果较弱且更依赖具体概念，同时伴随跨特质溢出效应。这表明即便对大量概念选择性神经元进行干预，也难以实现对生成标签的同等可控性。综上，我们的发现揭示了LLMs中表征控制与行为控制之间的差距。