© 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. 54219
    Prev
    Next
    INDEX
    Explanations

    information related to sports rankings and performance statistics

    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
     force
    -0.07
    еÑĢе
    -0.06
    indered
    -0.06
     Force
    -0.06
     tip
    -0.06
    uong
    -0.06
     FORCE
    -0.06
    636
    -0.05
    ÎķÎĻ
    -0.05
    .sparse
    -0.05
    POSITIVE LOGITS
    Ł
    0.08
    /archive
    0.07
    ç§ijæĬĢæľīéĻIJåħ¬åı¸
    0.07
    kinson
    0.07
    asd
    0.06
     Fut
    0.06
    vara
    0.06
    /upload
    0.06
    ãĢĤãģĤ
    0.06
     Baldwin
    0.06
    Activations Density 0.007%

    No Known Activations