© 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. 9-LLAMASCOPE-RES-131K
    11. 98833
    Prev
    Next
    INDEX
    Explanations

    references to racing events or stages

    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
    uds
    -0.06
    аÑĢа
    -0.06
    arges
    -0.06
    ноÑģи
    -0.06
    hausen
    -0.06
    оÑĢа
    -0.06
    pell
    -0.06
    rů
    -0.06
    iegel
    -0.06
    ÑģÑĤоÑı
    -0.06
    POSITIVE LOGITS
    odyn
    0.07
    utter
    0.06
    боÑĢ
    0.06
    Wrapped
    0.06
    arna
    0.06
    à¹Īà¸ĩ
    0.06
    azon
    0.06
    opsis
    0.06
    malar
    0.06
    QL
    0.06
    Activations Density 0.000%

    No Known Activations