Overview
Terms with dotted underlines have definitions! Hover over them to see explanations.
Wisent-Guard uses representation engineering to make your AI safer and more trustworthy. Unlock the true potential of your LLM with layer-level control.
With our tools, you can cut hallucinations by 43% and harmful responses by 88%. All through the power of controlling intermediate representations-thoughts hidden deep inside the AI brain.
State-of-the-art LLM Safeguards
Flexible latent space monitoring tool for blocking unwelcome responses. Reduces hallucinations by 43%, up to 7x the next best alternative. Can be used for various purposes including security, hallucinations, quality assurance.
Generalized Representation Engineering Framework
With its modular architecture, enables flexible modifications, creating a performant and usable framework for identifying and manipulating representations for safeguarding, performance improvement or evaluation.
Model-Agnostic
Works with all open source models.
CUDA/MPS/CPU Support
Built-in support for CUDA, MPS (Metal Performance Shaders) or CPU to make the guard work with variety of GPU Architectures
Support for over 6000 tasks
Use built in benchmarks using our lm-harness integration to create your own representations from common benchmarks like MMLU, TruthfulQA, HellaSwag and others. Or, use your own dataset of contrastive pairs to create the perfect representation for your use case.
Full optimisation
Use our internal logic to optimise common representation engineering hyper parameters like layer choice, classifier choice and steering strength to maximise the performance on your benchmarks.
Oversight
Save your results and understand the internal logic with built-in tools for logging and error handling
Performance speedup
Reduce the impact of this tech on your performance by having optimised performance in the background
Stay in the loop. Never miss out.
Subscribe to our newsletter and unlock Wisent insights.