© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 63190
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptive phrases related to artistic creativity and visual aesthetics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    utters
    -0.07
    вÑĸÑĤ
    -0.07
    aura
    -0.07
    reflection
    -0.06
    [sizeof
    -0.06
    raman
    -0.06
    Ïħγ
    -0.06
    ulan
    -0.06
    ÙĪÛĮس
    -0.06
     Gros
    -0.06
    POSITIVE LOGITS
    TypeInfo
    0.07
    elia
    0.07
    edly
    0.07
    sville
    0.07
    stdexcept
    0.07
    ingly
    0.06
    ses
    0.06
     individually
    0.06
    edic
    0.06
     stuff
    0.06
    Activations Density 0.034%

    No Known Activations