© 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. 78354
    Prev
    Next
    INDEX
    Explanations

    references to sports outcomes and player performance analysis

    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
     -----------------------------------------------------------------------------↵
    -0.07
    θοÏĤ
    -0.07
    elay
    -0.07
    ανά
    -0.07
    ToPoint
    -0.07
     meis
    -0.07
     пÑĢиÑĩ
    -0.07
    ůl
    -0.06
    \Backend
    -0.06
    InitialState
    -0.06
    POSITIVE LOGITS
     margin
    0.08
    Prediction
    0.06
     Prediction
    0.06
    margin
    0.06
     margins
    0.06
     will
    0.06
     trend
    0.06
     Trend
    0.06
    Margin
    0.06
     bet
    0.06
    Activations Density 0.013%

    No Known Activations