© 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. 5873
    Prev
    Next
    INDEX
    Explanations

    phrases related to hosting events or gatherings

    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
    ccione
    -0.07
    reich
    -0.07
    ingly
    -0.07
    ackle
    -0.07
    adamente
    -0.06
    AMA
    -0.06
    ávÄĽ
    -0.06
     nÃło
    -0.06
    ens
    -0.06
    ç´ļ
    -0.06
    POSITIVE LOGITS
     a
    0.07
    olare
    0.07
     two
    0.07
     an
    0.07
    alled
    0.06
    alling
    0.06
     several
    0.06
    edl
    0.06
    entar
    0.06
     another
    0.06
    Activations Density 0.014%

    No Known Activations