© 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. 5871
    Prev
    Next
    INDEX
    Explanations

    references to artistic and cultural performance activities

    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
     firm
    -0.06
     worldwide
    -0.06
     millions
    -0.06
     ><?
    -0.06
     outs
    -0.06
     replacement
    -0.06
    Global
    -0.06
    .just
    -0.06
     global
    -0.06
    GLOBAL
    -0.06
    POSITIVE LOGITS
    perimental
    0.08
    ushman
    0.08
    åĩºåĵģ
    0.07
    ioneer
    0.07
    cul
    0.07
     micron
    0.07
    ãĥ¼ãĥŀ
    0.07
    experimental
    0.06
    EXIT
    0.06
    filepath
    0.06
    Activations Density 0.059%

    No Known Activations