# Probing deception, bias and beliefs

Area: [Mechanistic interpretability](https://mlsanity.com/mechinterp/index.md). HTML: https://mlsanity.com/mechinterp/probing-deception-bias-and-beliefs/

## Key facts

- Probing deception, bias and beliefs: 88 papers on arXiv since 2023 (data through 14 Oct 2026).
- 12 of its 88 mapped papers (14%) cite “Detecting Strategic Deception Using Linear Probes” (2025, arXiv 2502.03407).
- 2 of its 88 mapped papers (2%) cite “Localizing Lying in Llama: Understanding Instructed Dishonesty on True-False Questions Through Prompting, Probing, and Patching” (2023, arXiv 2311.15131).
- 8 new papers 24 Sep–14 Oct.

## Most cited here

- [Detecting Strategic Deception Using Linear Probes](https://mlsanity.com/paper/2502.03407/) (2025), cited by 12 papers here
- [Localizing Lying in Llama: Understanding Instructed Dishonesty on True-False Questions Through Prompting, Probing, and Patching](https://mlsanity.com/paper/2311.15131/) (2023), cited by 2 papers here
- [Linear Representations of Political Perspective Emerge in Large Language Models](https://mlsanity.com/paper/2503.02080/) (2025), cited by 2 papers here
- [Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective](https://mlsanity.com/paper/2506.05166/) (2025), cited by 2 papers here
- [Revisiting In-context Learning Inference Circuit in Large Language Models](https://mlsanity.com/paper/2410.04468/) (2024), cited by 1 papers here
- [Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare](https://mlsanity.com/paper/2502.13319/) (2025), cited by 1 papers here
- [Unsupervised Concept Vector Extraction for Bias Control in LLMs](https://mlsanity.com/paper/2502.19721/) (2025), cited by 1 papers here
- [FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering](https://mlsanity.com/paper/2504.14492/) (2025), cited by 1 papers here
- [Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs](https://mlsanity.com/paper/2505.15524/) (2025), cited by 1 papers here
- [When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models](https://mlsanity.com/paper/2506.04909/) (2025), cited by 1 papers here

## New (24 Sep–14 Oct)

- [Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering](https://mlsanity.com/paper/2610.19359/) (2026-10-14)
- [Rule vs.Consequence: Dissociable Internal Representations of Moral Reasoning in LLMs](https://mlsanity.com/paper/2610.16371/) (2026-10-12)
- [Latent space bias directions in LLMs capture confidence, not fairness](https://mlsanity.com/paper/2610.08559/) (2026-10-06)
- [Will the Judge Flip? Predicting Position-Sensitive LLM Judgments from Residual Stream Activations](https://mlsanity.com/paper/2610.07115/) (2026-10-05)
- [Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering](https://mlsanity.com/paper/2610.05894/) (2026-10-05)
- [Feature Elicitation for SAE Steering of Deceptive Behaviour in Small LLMs](https://mlsanity.com/paper/2610.20638/) (2026-10-02)
- [Right Answer, Wrong Mechanism: Detecting Pernicious Divergence in Causal Interventions](https://mlsanity.com/paper/2609.39243/) (2026-09-30)
- [The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining](https://mlsanity.com/paper/2609.32964/) (2026-09-26)