© 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. 80775
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding female representation and gender dynamics

    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
    uge
    -0.07
    utter
    -0.07
    .shiro
    -0.07
    umni
    -0.06
    alars
    -0.06
     Sno
    -0.06
    letal
    -0.06
    amarin
    -0.06
     elit
    -0.06
    enville
    -0.06
    POSITIVE LOGITS
     women
    0.22
     female
    0.22
     male
    0.21
     females
    0.19
     gender
    0.19
     Female
    0.19
     Women
    0.18
     males
    0.17
    Women
    0.17
     woman
    0.17
    Activations Density 0.006%

    No Known Activations