# Confidence Regulation Neurons in Language Models

arXiv: https://arxiv.org/abs/2406.16254 · HTML: https://mlsanity.com/paper/2406.16254/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 79 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Builds on (most cited first, 30 of 55)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)

## Built on by (most cited first, 30 of 57)

- [Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs](https://mlsanity.com/paper/2407.01082/) (2024)
- [A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models](https://mlsanity.com/paper/2407.02646/) (2024)
- [Knowledge Mechanisms in Large Language Models: A Survey and Perspective](https://mlsanity.com/paper/2407.15017/) (2024)
- [How do LLMs Compute Verbal Confidence](https://mlsanity.com/paper/2603.17839/) (2026)
- [Transferring Linear Features Across Language Models With Model Stitching](https://mlsanity.com/paper/2506.06609/) (2025)
- [Dense SAE Latents Are Features, Not Bugs](https://mlsanity.com/paper/2506.15679/) (2025)
- [How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence](https://mlsanity.com/paper/2504.02904/) (2025)
- [Emergence of Linear Truth Encodings in Language Models](https://mlsanity.com/paper/2510.15804/) (2025)
- [You can remove GPT2's LayerNorm by fine-tuning](https://mlsanity.com/paper/2409.13710/) (2024)
- [Mitigating Copy Bias in In-Context Learning through Neuron Pruning](https://mlsanity.com/paper/2410.01288/) (2024)
- [Calibration Across Layers: Understanding Calibration Evolution in LLMs](https://mlsanity.com/paper/2511.00280/) (2025)
- [Geometry of Decision Making in Language Models](https://mlsanity.com/paper/2511.20315/) (2025)
- [Closing the Confidence-Faithfulness Gap in Large Language Models](https://mlsanity.com/paper/2603.25052/) (2026)
- [Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability](https://mlsanity.com/paper/2507.02559/) (2025)
- [Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region](https://mlsanity.com/paper/2502.13946/) (2025)
- [Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models](https://mlsanity.com/paper/2508.02360/) (2025)
- [Hallucinations Undermine Trust; Metacognition is a Way Forward](https://mlsanity.com/paper/2605.01428/) (2026)
- [Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement](https://mlsanity.com/paper/2505.23183/) (2025)
- [Isolating Culture Neurons in Multilingual Large Language Models](https://mlsanity.com/paper/2508.02241/) (2025)
- [Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering](https://mlsanity.com/paper/2601.19847/) (2026)
- [The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models](https://mlsanity.com/paper/2602.08159/) (2026)
- [Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs](https://mlsanity.com/paper/2604.01457/) (2026)
- [The Weight Norm Sets the Grokking Timescale: A Causal Delay Law](https://mlsanity.com/paper/2606.13753/) (2026)
- [Prediction hubs are context-informed frequent tokens in LLMs](https://mlsanity.com/paper/2502.10201/) (2025)
- [Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models](https://mlsanity.com/paper/2503.21718/) (2025)
- [Understanding Post-Training Structural Changes in Large Language Models](https://mlsanity.com/paper/2509.17866/) (2025)
- [Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty](https://mlsanity.com/paper/2511.12991/) (2025)
- [Suppressing Final Layer Hidden State Jumps in Transformer Pretraining](https://mlsanity.com/paper/2601.18302/) (2026)
- [Disentangling MLP Neuron Weights in Vocabulary Space](https://mlsanity.com/paper/2604.06005/) (2026)
- [Emergent Specialization: Rare Token Neurons in Language Models](https://mlsanity.com/paper/2505.12822/) (2025)

## Abstract (arXiv)

Despite their widespread use, the mechanisms by which large language models (LLMs) represent and regulate uncertainty in next-token predictions remain largely unexplored. This study investigates two critical components believed to influence this uncertainty: the recently discovered entropy neurons and a new set of components that we term token frequency neurons. Entropy neurons are characterized by an unusually high weight norm and influence the final layer normalization (LayerNorm) scale to effectively scale down the logits. Our work shows that entropy neurons operate by writing onto an unembedding null space, allowing them to impact the residual stream norm with minimal direct effect on the logits themselves. We observe the presence of entropy neurons across a range of models, up to 7 billion parameters. On the other hand, token frequency neurons, which we discover and describe here for the first time, boost or suppress each token's logit proportionally to its log frequency, thereby shifting the output distribution towards or away from the unigram distribution. Finally, we present a detailed case study where entropy neurons actively manage confidence in the setting of induction, i.e. detecting and continuing repeated subsequences.