© 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. 38272
    Prev
    Next
    INDEX
    Explanations

    pronouns that refer to male individuals

    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
     itself
    -0.08
    ovit
    -0.08
    andon
    -0.08
     ÑģобоÑİ
    -0.08
    ousel
    -0.07
     Ä°Åŀ
    -0.07
    ange
    -0.07
    arakter
    -0.07
    (es
    -0.07
    enance
    -0.07
    POSITIVE LOGITS
    /she
    0.12
    zelf
    0.10
    'll
    0.10
    /her
    0.10
    've
    0.10
    're
    0.09
    ’re
    0.09
    ’ll
    0.08
    ila
    0.08
    ela
    0.08
    Activations Density 0.419%

    No Known Activations