Activation steering methods are widely used to control large language model (LLM) behavior and are often interpreted as revealing meaningful internal representations. This interpretation assumes steering directions are identifiable and uniquely recoverable from input-output behavior. We show that, under white-box single-layer access, steering vectors are fundamentally non-identifiable due to large equivalence classes of behaviorally indistinguishable interventions. Empirically, we show that orthogonal perturbations achieve near-equivalent efficacy with negligible effect sizes across multiple models and traits. Critically, we show that the non-identifiability is a robust geometric property that persists across diverse prompt distributions. These findings reveal fundamental interpretability limits and highlight the need for structural constraints beyond behavioral testing to enable reliable alignment interventions.

翻译：激活导向方法被广泛用于控制大型语言模型（LLM）的行为，并常被解释为揭示了有意义的内部表征。这种解释假定导向方向是可识别的，并能从输入-输出行为中唯一地恢复。我们证明，在白盒单层访问条件下，由于存在大量行为上无法区分的干预所构成的等价类，导向向量本质上是不可识别的。通过实证研究，我们表明正交扰动在多个模型和多种特性上都能达到近乎等效的效果，且效应量可忽略不计。关键的是，我们证明了这种不可识别性是一种稳健的几何特性，在不同的提示分布下持续存在。这些发现揭示了可解释性的根本局限，并强调了需要超越行为测试的结构性约束，以实现可靠的对齐干预。