© 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. 1272
    Prev
    Next
    INDEX
    Explanations

    event-related information, specifically regarding performances and celebrations

    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
     Dw
    -0.06
    ocaly
    -0.06
    &m
    -0.06
    ierz
    -0.06
    mb
    -0.06
    KA
    -0.05
    ka
    -0.05
     Brewing
    -0.05
     Lawrence
    -0.05
    633
    -0.05
    POSITIVE LOGITS
    datable
    0.07
     DISCLAIM
    0.07
    ÑĢÑĥг
    0.07
    ãĤ¤ãĤº
    0.07
    ÑĨеп
    0.07
    asje
    0.07
     PERFORMANCE
    0.07
    ãĥķãĥ¬
    0.06
    anship
    0.06
    à¥įतà¤ķ
    0.06
    Activations Density 0.010%

    No Known Activations