# Mechanistic Interpretability of Socio-Political Frames in Language Models

arXiv: https://arxiv.org/abs/2510.03799 · HTML: https://mlsanity.com/paper/2510.03799/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Probing deception, bias and beliefs, one of 13 directions in Mechanistic interpretability.
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 4 Oct 2025.

## Placed in

- Mechanistic interpretability / [Probing deception, bias and beliefs](https://mlsanity.com/mechinterp/probing-deception-bias-and-beliefs/)

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [Language Models Represent Space and Time](https://mlsanity.com/paper/2310.02207/) (2023)
- [A Systematic Investigation of Commonsense Knowledge in Large Language Models](https://mlsanity.com/paper/2111.00607/) (2021)
- [Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages](https://mlsanity.com/paper/2203.14139/) (2022)
- [FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning](https://mlsanity.com/paper/2302.04834/) (2023)

## Abstract (arXiv)

This paper explores the ability of large language models 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' and `nurturing 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.