© 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. 73640
    Prev
    Next
    INDEX
    Explanations

    references to players and their 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
    airo
    -0.07
    ono
    -0.07
    otics
    -0.07
     Göz
    -0.07
    .cg
    -0.07
    ej
    -0.06
    ibold
    -0.06
    нож
    -0.06
    ائÙħ
    -0.06
    اتÙĩ
    -0.06
    POSITIVE LOGITS
     hometown
    0.06
     debut
    0.06
    oyal
    0.06
    rier
    0.06
     en
    0.06
     three
    0.06
    enko
    0.05
     last
    0.05
     port
    0.05
    Currency
    0.05
    Activations Density 0.015%

    No Known Activations