© 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. 86407
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports strategies and player performances

    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
    iron
    -0.07
    inx
    -0.07
     actionTypes
    -0.06
     Infer
    -0.06
    itches
    -0.06
    arios
    -0.06
     EntityState
    -0.06
    ¿
    -0.06
     Employ
    -0.06
     whit
    -0.06
    POSITIVE LOGITS
    kiye
    0.07
    uming
    0.07
    _MISC
    0.07
    MMdd
    0.07
     flank
    0.07
    createQuery
    0.07
     Moff
    0.07
     Ãĸr
    0.06
    CHAIN
    0.06
     Fi
    0.06
    Activations Density 0.013%

    No Known Activations