© 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 EvalsExportsAPI 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. 29114
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events, specifically predictions and performances of teams and players

    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
    apos
    -0.08
    quat
    -0.08
    isher
    -0.07
     representative
    -0.07
    بت
    -0.07
    hurst
    -0.07
    ajs
    -0.07
     fou
    -0.07
    represent
    -0.07
    ضر
    -0.06
    POSITIVE LOGITS
     Whisper
    0.06
     Solid
    0.06
    .Ok
    0.06
    .Solid
    0.06
    Naming
    0.06
    -solid
    0.06
    лÑİÑĩа
    0.06
    ahoma
    0.06
    /misc
    0.05
    ARIO
    0.05
    Activations Density 0.020%

    No Known Activations