Exploitation Without Deception: Dark Triad Feature Steering Reveals Separable Antisocial Circuits in Language Models

TL;DR

This paper demonstrates that Dark Triad traits in language models can be amplified through feature steering, revealing separable antisocial components that influence behavior without affecting deception capabilities.

Contribution

It introduces a method to amplify and analyze antisocial traits in language models, showing these traits are dissociable and operate through distinct computational pathways.

Findings

Steered models show increased exploitative and aggressive behavior (d=10.62).

Cognitive empathy remains unaffected despite increased antisocial traits.

Deception ability is unchanged, indicating dissociable antisocial and deceptive pathways.

Abstract

We use sparse autoencoder (SAE) feature steering to amplify Dark Triad personality traits (Machiavellianism, narcissism, and psychopathy) in Llama-3.3-70B-Instruct and evaluate the resulting behavioral changes across five psychological instruments. The steered model becomes substantially more exploitative, aggressive, and callous on novel behavioral scenarios (d=10.62) while its cognitive empathy remains intact, reproducing the empathy dissociation characteristic of human Dark Triad populations. Critically, strategic deception is completely unaffected across all features, suggesting that exploitation and deception may operate through dissociable computational pathways in large language models. Individual feature analysis reveals non-redundant encoding, with each feature driving distinct antisocial mechanisms through separable computational pathways. We also show that feature discovery method itself modulates intervention depth: contrastively-discovered features change both self-report and behavior, while semantically-searched features change only self-report (d=12.65 between methods on behavior). These findings suggest that antisocial tendencies in at least one large language model comprise dissociable components rather than a unified construct, with implications for how such tendencies should be detected, measured, and controlled.