© 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. 78428
    Prev
    Next
    INDEX
    Explanations

    details related to specific football plays and game statistics

    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
    enheim
    -0.07
    ngth
    -0.07
     Hispan
    -0.07
    ÐĴÑĤ
    -0.06
    iously
    -0.06
    ekil
    -0.06
    ofilm
    -0.06
    imei
    -0.06
    ocale
    -0.06
    polator
    -0.06
    POSITIVE LOGITS
    æŁ±
    0.07
    awai
    0.06
     outskirts
    0.06
     Huff
    0.06
     Corn
    0.06
    ê
    0.06
    unte
    0.06
    iete
    0.06
    prom
    0.06
    ovou
    0.06
    Activations Density 0.003%

    No Known Activations