© 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. 96000
    Prev
    Next
    INDEX
    Explanations

    mentions of "others" or references to groups separate from the speaker

    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
    еÑĢи
    -0.06
    piel
    -0.06
    anh
    -0.06
    ses
    -0.06
     ullam
    -0.06
    ig
    -0.06
    ISMATCH
    -0.06
    enstein
    -0.06
    nt
    -0.06
    lope
    -0.06
    POSITIVE LOGITS
    ιÏĥÏĦο
    0.07
     who
    0.07
     Tos
    0.07
    ylim
    0.07
    preter
    0.07
    pollo
    0.07
    /vendors
    0.07
    /groups
    0.06
    -than
    0.06
     whom
    0.06
    Activations Density 0.019%

    No Known Activations