© 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. 41848
    Prev
    Next
    INDEX
    Explanations

    references to Google Cloud Bigtable and its related APIs

    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
    indre
    -0.07
    ourg
    -0.06
    uters
    -0.06
    issen
    -0.06
    zell
    -0.06
    vere
    -0.06
    ston
    -0.06
     tribe
    -0.06
     Durant
    -0.06
     Ferguson
    -0.06
    POSITIVE LOGITS
    erne
    0.07
     addCriterion
    0.07
    insky
    0.07
    yleft
    0.07
    rzy
    0.06
    .openg
    0.06
    robat
    0.06
    emann
    0.06
    _Row
    0.06
    SqlParameter
    0.06
    Activations Density 0.009%

    No Known Activations