# Neuron-Level Differentiation of Memorization and Generalization in Large Language Models

arXiv: https://arxiv.org/abs/2412.18497 · HTML: https://mlsanity.com/paper/2412.18497/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 16 of 16)

- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Deduplicating Training Data Makes Language Models Better](https://mlsanity.com/paper/2107.06499/) (2021)
- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Improving Instruction-Following in Language Models through Activation Steering](https://mlsanity.com/paper/2410.12877/) (2024)
- [Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization](https://mlsanity.com/paper/2406.00045/) (2024)
- [On Memorization of Large Language Models in Logical Reasoning](https://mlsanity.com/paper/2410.23123/) (2024)
- [Rethinking LLM Memorization through the Lens of Adversarial Compression](https://mlsanity.com/paper/2404.15146/) (2024)
- [Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation](https://mlsanity.com/paper/2102.01818/) (2021)
- [Demystifying Verbatim Memorization in Large Language Models](https://mlsanity.com/paper/2407.17817/) (2024)
- [Can LLM Graph Reasoning Generalize beyond Pattern Memorization?](https://mlsanity.com/paper/2406.15992/) (2024)
- [Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution](https://mlsanity.com/paper/2410.00153/) (2024)
- [Steering Large Language Models between Code Execution and Textual Reasoning](https://mlsanity.com/paper/2410.03524/) (2024)
- [Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs](https://mlsanity.com/paper/2405.11880/) (2024)

## Built on by (most cited first, 2 of 2)

- [Beyond Frequency: The Role of Redundancy in Large Language Model Memorization](https://mlsanity.com/paper/2506.12321/) (2025)
- [Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs](https://mlsanity.com/paper/2506.17630/) (2025)

## Abstract (arXiv)

We investigate how Large Language Models (LLMs) distinguish between memorization and generalization at the neuron level. Through carefully designed tasks, we identify distinct neuron subsets responsible for each behavior. Experiments on both a GPT-2 model trained from scratch and a pretrained LLaMA-3.2 model fine-tuned with LoRA show consistent neuron-level specialization. We further demonstrate that inference-time interventions on these neurons can steer the model's behavior toward memorization or generalization. To assess robustness, we evaluate intra-task and inter-task consistency, confirming that these neuron-behavior associations reflect generalizable patterns rather than dataset-specific artifacts. Our findings reveal modular structure in LLMs and enable controlling memorization and generalization behaviors at inference time.