© 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. 56811
    Prev
    Next
    INDEX
    Explanations

    phrases related to community support and local initiatives

    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
     вп
    -0.07
    ordon
    -0.07
    нÑĤ
    -0.06
    едаг
    -0.06
    criptive
    -0.06
    emente
    -0.06
    essage
    -0.06
    меÑĢик
    -0.06
     Downtown
    -0.06
     packet
    -0.06
    POSITIVE LOGITS
    .gov
    0.07
    WithType
    0.07
    .opend
    0.07
     external
    0.07
     Embed
    0.06
    .external
    0.06
    Embed
    0.06
    external
    0.06
    ubar
    0.06
    imoto
    0.06
    Activations Density 0.073%

    No Known Activations