# bbycroft/llm-viz

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/bbycroft-llm-viz).**

5,260 stars · 613 forks · TypeScript

## Links

- GitHub: https://github.com/bbycroft/llm-viz
- Homepage: https://bbycroft.net
- awesome-repositories: https://awesome-repositories.com/repository/bbycroft-llm-viz.md

## Description

llm-viz is a 3D architecture visualizer and inference simulator for large language models. It provides a visual representation of network topology and the mathematical operations used during the process of generating a response.

The tool enables the exploration of internal weight distributions and the layout of layers within a neural network. It facilitates model interpretability and inference debugging by tracking the step-by-step movement of data through the architecture.

The system utilizes GPU-accelerated 3D rendering to visualize tensor flow and spatial mappings of weights. It includes capabilities for static model analysis and instruction-step playback to synchronize the visual state of the network with sequential execution.

## Tags

### Artificial Intelligence & ML

- [Architecture Visualizations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/transformer-architectures/architecture-visualizations.md) — Offers interactive 3D graphical representations of the internal components and operations of LLM architectures.
- [Model Interpretability](https://awesome-repositories.com/f/artificial-intelligence-ml/model-interpretability.md) — Enables visual understanding of complex transformer architectures to make internal workings more transparent.
- [Architecture Visualizers](https://awesome-repositories.com/f/artificial-intelligence-ml/model-visualization-tools/architecture-visualizers.md) — Provides a 3D visualizer for the internal structure and data flow of large language models.
- [Neural Network Explorers](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-explorers.md) — Provides an interactive tool for exploring the layout and data flow of weights and layers in neural networks.
- [Inference Step Executions](https://awesome-repositories.com/f/artificial-intelligence-ml/step-based-schedulers/step-execution-engines/inference-step-executions.md) — Implements a visual playback system to step through individual inference forward passes for a single token.
- [Inference Simulators](https://awesome-repositories.com/f/artificial-intelligence-ml/step-based-schedulers/step-execution-engines/inference-step-executions/inference-simulators.md) — Offers a visual walkthrough of the step-by-step process used by a large language model to generate a response.
- [Inference Visualizations](https://awesome-repositories.com/f/artificial-intelligence-ml/step-based-schedulers/step-execution-engines/inference-step-executions/inference-visualizations.md) — Renders the network topology and mathematical operations to show the step-by-step process of generating a response. ([source](https://bbycroft.net))
- [Model Weight Visualizations](https://awesome-repositories.com/f/artificial-intelligence-ml/model-weight-visualizations.md) — Maps individual model parameters to 3D coordinates to visualize the physical distribution of weights.
- [Neural Network Debugging](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-debugging.md) — Facilitates debugging by tracking the step-by-step movement of data through the network during generation.
- [Neural Network Visualizations](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-visualizations.md) — Generates graphical representations of neural network architectures and layers to study weight distributions.

### Security & Cryptography

- [Topology Visualizers](https://awesome-repositories.com/f/security-cryptography/network-access-control/topology-visualizers.md) — Provides a 3D model of the network architecture to illustrate how data flows during inference. ([source](https://cdn.jsdelivr.net/gh/bbycroft/llm-viz@main/README.md))

### Data & Databases

- [Tensor Flow Animations](https://awesome-repositories.com/f/data-databases/data-processing-pipelines/data-transformation/array-tensor-manipulation/tensor-transformations/tensor-flow-animations.md) — Visualizes the movement and transformation of data tensors as they pass through different model layers during inference.

### Graphics & Multimedia

- [3D Scene Renderers](https://awesome-repositories.com/f/graphics-multimedia/graphics-engines-rendering/rendering/systems/gpu-accelerated-ui-rendering/3d-scene-renderers.md) — Provides a hardware-accelerated 3D renderer for real-time visualization of complex neural network topologies.

### Software Engineering & Architecture

- [Model Architecture Analysis](https://awesome-repositories.com/f/software-engineering-architecture/static-analysis/model-architecture-analysis.md) — Parses pre-trained weight files to extract and render the fixed structural layout of the model architecture.