© 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. 16516
    Prev
    Next
    INDEX
    Explanations

    dialogue or quotes attributed to speakers

    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
    ãģ«ãģĹãģ¦
    -0.07
    [email
    -0.07
    intro
    -0.07
    .ColumnHeader
    -0.07
    oÄŁlu
    -0.06
    ulumi
    -0.06
    -Sah
    -0.06
    /GPL
    -0.06
    à¤ľà¤¨
    -0.06
     MediaType
    -0.06
    POSITIVE LOGITS
    agal
    0.07
    abal
    0.07
    abbo
    0.07
    achs
    0.07
    elve
    0.06
    iasm
    0.06
    wan
    0.06
    ulan
    0.06
    ãĥ´
    0.06
    ÑĢиг
    0.06
    Activations Density 0.033%

    No Known Activations