© 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. 70281
    Prev
    Next
    INDEX
    Explanations

    team performance metrics and game results 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
    Typed
    -0.07
    ÙĩÙĩ
    -0.07
     Fantasy
    -0.06
    ambre
    -0.06
    .mvc
    -0.06
    rette
    -0.06
     cref
    -0.06
    eca
    -0.06
    arden
    -0.06
    à¥ģà¤ģ
    -0.06
    POSITIVE LOGITS
     beat
    0.08
     beats
    0.07
     beating
    0.07
    beat
    0.07
    Beat
    0.06
     defeat
    0.06
     defeats
    0.06
    uper
    0.06
     Beat
    0.06
    -ahead
    0.06
    Activations Density 0.045%

    No Known Activations