© 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 EvalsExportsAPI 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. 78540
    Prev
    Next
    INDEX
    Explanations

    references to scoring chances and goal attempts in a sports context

    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
    _IL
    -0.08
    εδ
    -0.07
    iske
    -0.07
     Chap
    -0.07
    æŁĦ
    -0.06
    essim
    -0.06
    ÙĦÛĮسÛĮ
    -0.06
    undy
    -0.06
    ipo
    -0.06
    ANCH
    -0.06
    POSITIVE LOGITS
     harm
    0.07
    ahlen
    0.06
    iyon
    0.06
    .Exists
    0.06
    ourn
    0.06
    letal
    0.06
    RN
    0.06
    omik
    0.06
    EXT
    0.06
     instead
    0.05
    Activations Density 0.003%

    No Known Activations