# Large Multi-modal Models Can Interpret Features in Large Multi-modal Models

arXiv: https://arxiv.org/abs/2411.14982 · HTML: https://mlsanity.com/paper/2411.14982/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 20 of its 41 references that are in the map.
- First posted on arXiv 22 Nov 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)
- Mechanistic interpretability / [Interpreting vision and multimodal models](https://mlsanity.com/mechinterp/interpreting-vision-and-multimodal-models/)

## Builds on (most cited first, 20 of 20)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [Reducing Hallucinations in Vision-Language Models via Latent Space Steering](https://mlsanity.com/paper/2410.15778/) (2024)
- [A Concept-Based Explainability Framework for Large Multimodal Models](https://mlsanity.com/paper/2406.08074/) (2024)
- [Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?](https://mlsanity.com/paper/2404.03411/) (2024)
- [Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization](https://mlsanity.com/paper/1310.7991/) (2013)

## Built on by (most cited first, 23 of 23)

- [Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models](https://mlsanity.com/paper/2504.02821/) (2025)
- [SAE-V: Interpreting Multimodal Models for Enhanced Alignment](https://mlsanity.com/paper/2502.17514/) (2025)
- [Visual Representations inside the Language Model](https://mlsanity.com/paper/2510.04819/) (2025)
- [LangBridge: Interpreting Image as a Combination of Language Embeddings](https://mlsanity.com/paper/2503.19404/) (2025)
- [From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens](https://mlsanity.com/paper/2510.02292/) (2025)
- [SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions](https://mlsanity.com/paper/2507.23784/) (2025)
- [SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination](https://mlsanity.com/paper/2512.07730/) (2025)
- [Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering](https://mlsanity.com/paper/2602.00621/) (2026)
- [Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models](https://mlsanity.com/paper/2604.25011/) (2026)
- [Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers](https://mlsanity.com/paper/2606.06664/) (2026)
- [Insights into a radiology-specialised multimodal large language model with sparse autoencoders](https://mlsanity.com/paper/2507.12950/) (2025)
- [Language Models Can Explain Visual Features via Steering](https://mlsanity.com/paper/2603.22593/) (2026)
- [Improving Sparse Autoencoder with Dynamic Attention](https://mlsanity.com/paper/2604.14925/) (2026)
- [Beyond Semantics: Disentangling Information Scope in Sparse Autoencoders for CLIP](https://mlsanity.com/paper/2604.05724/) (2026)
- [When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities](https://mlsanity.com/paper/2607.08605/) (2026)
- [Visual concept ranking uncovers medical shortcuts used by large multimodal models](https://mlsanity.com/paper/2602.05096/) (2026)
- [Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs](https://mlsanity.com/paper/2604.08846/) (2026)
- [The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes](https://mlsanity.com/paper/2606.11470/) (2026)
- [The Hidden Evolution of Disguised Visual Context inside the VLM](https://mlsanity.com/paper/2606.20077/) (2026)
- [Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders](https://mlsanity.com/paper/2606.29888/) (2026)
- [Latent Cluster Analysis for Vision-Language-Action Models](https://mlsanity.com/paper/2609.02634/) (2026)
- [Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation Enforcement](https://mlsanity.com/paper/2609.24243/) (2026)
- [NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning](https://mlsanity.com/paper/2609.38098/) (2026)

## Abstract (arXiv)

Recent advances in Large Multimodal Models (LMMs) lead to significant breakthroughs in both academia and industry. One question that arises is how we, as humans, can understand their internal neural representations. This paper takes an initial step towards addressing this question by presenting a versatile framework to identify and interpret the semantics within LMMs. Specifically, 1) we first apply a Sparse Autoencoder(SAE) to disentangle the representations into human understandable features. 2) We then present an automatic interpretation framework to interpreted the open-semantic features learned in SAE by the LMMs themselves. We employ this framework to analyze the LLaVA-NeXT-8B model using the LLaVA-OV-72B model, demonstrating that these features can effectively steer the model's behavior. Our results contribute to a deeper understanding of why LMMs excel in specific tasks, including EQ tests, and illuminate the nature of their mistakes along with potential strategies for their rectification. These findings offer new insights into the internal mechanisms of LMMs and suggest parallels with the cognitive processes of the human brain.