# MambaLRP: Explaining Selective State Space Sequence Models

arXiv: https://arxiv.org/abs/2406.07592 · HTML: https://mlsanity.com/paper/2406.07592/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Core SSM architectures for language, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 69 of its 84 references that are in the map.
- First posted on arXiv 11 Jun 2024.

## Placed in

- State-space sequence models (S4, Mamba) / [Core SSM architectures for language](https://mlsanity.com/ssm/core-ssm-architectures-for-language/)

## Builds on (most cited first, 30 of 69)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers](https://mlsanity.com/paper/2110.13985/) (2021)
- [Hungry Hungry Hippos: Towards Language Modeling with State Space Models](https://mlsanity.com/paper/2212.14052/) (2022)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)

## Built on by (most cited first, 30 of 32)

- [DeciMamba: Exploring the Length Extrapolation Potential of Mamba](https://mlsanity.com/paper/2406.14528/) (2024)
- [A Survey of Mamba](https://mlsanity.com/paper/2408.01129/) (2024)
- [Language Model Circuits Are Sparse in the Neuron Basis](https://mlsanity.com/paper/2601.22594/) (2026)
- [The Clever Hans Effect in Unsupervised Learning](https://mlsanity.com/paper/2408.08041/) (2024)
- [RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching](https://mlsanity.com/paper/2508.21258/) (2025)
- [A Close Look at Decomposition-based XAI-Methods for Transformer Language Models](https://mlsanity.com/paper/2502.15886/) (2025)
- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features](https://mlsanity.com/paper/2408.17198/) (2024)
- [LaTIM: Measuring Latent Token-to-Token Interactions in Mamba Models](https://mlsanity.com/paper/2502.15612/) (2025)
- [Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability](https://mlsanity.com/paper/2506.02138/) (2025)
- [Position: We Need An Algorithmic Understanding of Generative AI](https://mlsanity.com/paper/2507.07544/) (2025)
- [Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs](https://mlsanity.com/paper/2506.13727/) (2025)
- [Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks](https://mlsanity.com/paper/2602.22719/) (2026)
- [Demystifying the Token Dynamics of Deep Selective State Space Models](https://mlsanity.com/paper/2410.03292/) (2024)
- [State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding](https://mlsanity.com/paper/2510.12160/) (2025)
- [Hidden State Poisoning Attacks against Mamba-based Language Models](https://mlsanity.com/paper/2601.01972/) (2026)
- [Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology](https://mlsanity.com/paper/2603.08328/) (2026)
- [How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits](https://mlsanity.com/paper/2605.08348/) (2026)
- [A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification](https://mlsanity.com/paper/2410.03296/) (2024)
- [Did Models Learn Sufficiently? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation](https://mlsanity.com/paper/2511.12100/) (2025)
- [Towards Understanding What State Space Models Learn About Code](https://mlsanity.com/paper/2602.06774/) (2026)
- [Selective State Space Memory for Large Vision-Language Models](https://mlsanity.com/paper/2412.09875/) (2024)
- [Observability conditions for neural state-space models with eigenvalues and their roots of unity](https://mlsanity.com/paper/2504.15758/) (2025)
- [Fast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structures](https://mlsanity.com/paper/2508.03913/) (2025)
- [Value bounds and Convergence Analysis for Averages of LRP attributions](https://mlsanity.com/paper/2509.08963/) (2025)
- [FoSS: Modeling Long Range Dependencies and Multimodal Uncertainty in Trajectory Prediction via Fourier State Space Integration](https://mlsanity.com/paper/2603.01284/) (2026)
- [A Circuit, Not The Circuit: Non-Unique Causal Localisation of the Mamba-2 State Sink](https://mlsanity.com/paper/2606.00930/) (2026)
- [Distributed Sparse Interventions in Language Models](https://mlsanity.com/paper/2607.07128/) (2026)
- [What Does Layer-Importance Reveal About Transformers and State-Space Models?](https://mlsanity.com/paper/2609.16537/) (2026)
- [ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers](https://mlsanity.com/paper/2609.17152/) (2026)

## Abstract (arXiv)

Recent sequence modeling approaches using selective state space sequence models, referred to as Mamba models, have seen a surge of interest. These models allow efficient processing of long sequences in linear time and are rapidly being adopted in a wide range of applications such as language modeling, demonstrating promising performance. To foster their reliable use in real-world scenarios, it is crucial to augment their transparency. Our work bridges this critical gap by bringing explainability, particularly Layer-wise Relevance Propagation (LRP), to the Mamba architecture. Guided by the axiom of relevance conservation, we identify specific components in the Mamba architecture, which cause unfaithful explanations. To remedy this issue, we propose MambaLRP, a novel algorithm within the LRP framework, which ensures a more stable and reliable relevance propagation through these components. Our proposed method is theoretically sound and excels in achieving state-of-the-art explanation performance across a diverse range of models and datasets. Moreover, MambaLRP facilitates a deeper inspection of Mamba architectures, uncovering various biases and evaluating their significance. It also enables the analysis of previous speculations regarding the long-range capabilities of Mamba models.