© 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. 76469
    Prev
    Next
    INDEX
    Explanations

    statistics and performance metrics in sports contexts

    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
     sant
    -0.07
    oldt
    -0.06
    ÑĢоÑĪ
    -0.06
    phies
    -0.06
    ople
    -0.06
    ẽ
    -0.06
    olds
    -0.06
    нина
    -0.06
    alph
    -0.06
    STALL
    -0.06
    POSITIVE LOGITS
    gee
    0.07
    zig
    0.07
    dro
    0.06
    .GraphicsUnit
    0.06
    Patch
    0.06
    404
    0.06
    ckett
    0.06
     since
    0.06
     pilots
    0.06
     tensors
    0.06
    Activations Density 0.008%

    No Known Activations