© 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. 17924
    Prev
    Next
    INDEX
    Explanations

    articles paired with adjectives that indicate size or quality

    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
    undry
    -0.07
    .xmlbeans
    -0.07
     Duy
    -0.06
    orex
    -0.06
     Fro
    -0.06
    éļ
    -0.06
    947
    -0.06
    eid
    -0.06
    inee
    -0.06
    zano
    -0.06
    POSITIVE LOGITS
    ifu
    0.07
     strange
    0.07
     funny
    0.07
    reich
    0.06
    aster
    0.06
    PERTIES
    0.06
    chers
    0.06
    ioned
    0.06
    IFA
    0.06
     Example
    0.06
    Activations Density 0.055%

    No Known Activations