© 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. 117729
    Prev
    Next
    INDEX
    Explanations

    adjectives that imply capability or capacity

    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
    reau
    -0.08
    rey
    -0.08
    edb
    -0.08
    osu
    -0.07
    .mdl
    -0.07
     ÎķÎĽ
    -0.07
    hung
    -0.07
    uras
    -0.07
    doc
    -0.07
    /dc
    -0.07
    POSITIVE LOGITS
    ably
    0.08
    /un
    0.08
     amount
    0.07
    antly
    0.07
     force
    0.07
     amounts
    0.07
    nes
    0.06
    /ext
    0.06
     quantities
    0.06
    vably
    0.06
    Activations Density 0.019%

    No Known Activations