© 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. 9-LLAMASCOPE-RES-131K
    11. 99254
    Prev
    Next
    INDEX
    Explanations

    issues related to women's rights and social justice

    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
    inker
    -0.07
    erce
    -0.07
    ulty
    -0.06
    adiens
    -0.06
    931
    -0.06
    ç«
    -0.06
    emez
    -0.06
    ibase
    -0.06
     Alive
    -0.06
    igger
    -0.06
    POSITIVE LOGITS
    ille
    0.07
    VRTX
    0.07
    ãĥªãĤ¢
    0.07
    odesk
    0.07
    Äįet
    0.07
    åĨĬ
    0.07
    ÙİØ£
    0.06
    GenerationStrategy
    0.06
    ledo
    0.06
    olution
    0.06
    Activations Density 0.136%

    No Known Activations