© 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. 92048
    Prev
    Next
    INDEX
    Explanations

    keywords related to location and regional classifications

    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
    icer
    -0.06
    amos
    -0.06
    iller
    -0.06
    ellig
    -0.06
     Vladim
    -0.06
    ipp
    -0.06
    asant
    -0.06
    ize
    -0.06
    aper
    -0.05
    .Loader
    -0.05
    POSITIVE LOGITS
    :///
    0.07
    uset
    0.07
    esar
    0.07
    缣
    0.07
    ExecutionContext
    0.07
    inis
    0.07
    SCRI
    0.06
    ìľĦìĽIJíļĮ
    0.06
    stag
    0.06
    eshire
    0.06
    Activations Density 0.002%

    No Known Activations