© 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. 86341
    Prev
    Next
    INDEX
    Explanations

    mentions of sports awards and distinctions relating to 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
    loquent
    -0.09
    aura
    -0.08
    AZY
    -0.08
    ãĥ¼ãĥĢ
    -0.07
    ixel
    -0.07
    ffen
    -0.07
    HeaderValue
    -0.07
    ibilit
    -0.07
    SDL
    -0.07
    ég
    -0.07
    POSITIVE LOGITS
    473
    0.07
     forward
    0.07
     Utility
    0.07
     utility
    0.07
    847
    0.07
     goalkeeper
    0.06
    848
    0.06
    443
    0.06
     gl
    0.06
     left
    0.06
    Activations Density 0.167%

    No Known Activations