Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 11455
    Prev
    Next
    INDEX
    Explanations

    specific events or actions related to legal issues and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Programs
    -0.07
     Services
    -0.07
     Related
    -0.07
     Requirements
    -0.07
     Results
    -0.07
     Features
    -0.07
     Studies
    -0.07
     Uses
    -0.06
     Functions
    -0.06
     Contributions
    -0.06
    POSITIVE LOGITS
     Knife
    0.13
     Needle
    0.12
     Spiral
    0.12
     Rope
    0.11
     Bubble
    0.11
     Splash
    0.11
     Flake
    0.11
     Bottle
    0.11
     Barrel
    0.11
     Stitch
    0.11
    Activations Density 0.465%

    No Known Activations