© 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. 55002
    Prev
    Next
    INDEX
    Explanations

    terms related to racing events and tracks

    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
     tennis
    -0.07
     Tennis
    -0.07
    chwitz
    -0.07
    razier
    -0.07
    prung
    -0.06
    901
    -0.06
    onis
    -0.06
    ebi
    -0.06
    buie
    -0.06
     rá
    -0.06
    POSITIVE LOGITS
     harness
    0.07
     Speedway
    0.07
     Harness
    0.07
     Sez
    0.06
     Benton
    0.06
    774
    0.06
    hest
    0.06
    775
    0.06
     direct
    0.06
     Dispatcher
    0.06
    Activations Density 0.004%

    No Known Activations