Mechanistic Interpretability of Socio-Political Frames in Language Models

Abstract: This paper explores the ability of LLMs to generate and recognize deep cognitive frames, particularly in socio-political contexts. We demonstrate that LLMs are highly fluent in generating texts that evoke specific frames and can recognize these frames in zero-shot settings. Inspired by mechanistic interpretability research, we investigate the location of the strict father' andnurturing parent' frames within the model's hidden representation, identifying singular dimensions that correlate strongly with their presence. Our findings contribute to understanding how LLMs capture and express meaningful human concepts.