© 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. 80921
    Prev
    Next
    INDEX
    Explanations

    references to small or marginalized groups within larger populations

    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
    adele
    -0.07
    illon
    -0.07
    onde
    -0.07
    ZY
    -0.07
    uela
    -0.06
    (fabs
    -0.06
     PROGMEM
    -0.06
    BUFFER
    -0.06
     æŃ
    -0.06
    ayan
    -0.06
    POSITIVE LOGITS
     handful
    0.15
     fewer
    0.13
     few
    0.13
     elite
    0.12
     select
    0.11
     minority
    0.11
    few
    0.11
     Few
    0.10
    elite
    0.10
     Elite
    0.09
    Activations Density 0.044%

    No Known Activations