© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127303
    Prev
    Next
    INDEX
    Explanations

    references to gender representation in the arts, particularly comics

    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
    uzzi
    -0.07
    rani
    -0.07
     Shell
    -0.06
     Sham
    -0.06
     team
    -0.06
    esel
    -0.06
    füg
    -0.06
     legal
    -0.06
    onas
    -0.06
    ãĥģãĥ¼ãĥł
    -0.06
    POSITIVE LOGITS
    (DBG
    0.07
    orra
    0.07
    .override
    0.07
    æĻ®
    0.06
     yıldır
    0.06
    ulse
    0.06
    _lit
    0.06
     pleasures
    0.06
    .sys
    0.06
     jihad
    0.06
    Activations Density 0.021%

    No Known Activations