© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 72553
    Prev
    Next
    INDEX
    Explanations

    information regarding sports, particularly motorsports

    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
    ouv
    -0.07
    ãİ
    -0.07
    .Dto
    -0.07
    âĸį
    -0.07
    _BP
    -0.07
    _cleanup
    -0.07
    елик
    -0.07
     ãĢį
    -0.07
    .EditValue
    -0.07
    oplay
    -0.07
    POSITIVE LOGITS
     locally
    0.07
     local
    0.07
     cru
    0.06
     Fore
    0.06
    .local
    0.06
     Cru
    0.06
    uffle
    0.05
     (
    0.05
     world
    0.05
     tenant
    0.05
    Activations Density 0.033%

    No Known Activations