© 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. 107402
    Prev
    Next
    INDEX
    Explanations

    numerical representations of scores and leads 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
    eldorf
    -0.07
    .Std
    -0.07
     gol
    -0.07
     à¹Ĩ
    -0.07
    riminator
    -0.07
    inkle
    -0.07
    opensource
    -0.06
    кÑĤа
    -0.06
    zap
    -0.06
    cial
    -0.06
    POSITIVE LOGITS
     difference
    0.08
    _SCOPE
    0.06
    ãĤ¸ãĥ¥
    0.06
     Difference
    0.06
    -plus
    0.06
     spread
    0.06
    itter
    0.06
    _gb
    0.06
     advantage
    0.06
    -${
    0.06
    Activations Density 0.002%

    No Known Activations