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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 54172
    Prev
    Next
    INDEX
    Explanations

    references to gender representation in media

    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
    _executor
    -0.07
    IRT
    -0.07
     Correspond
    -0.07
    _LOOKUP
    -0.07
     ëĭ¤ìļ´ë°Ľê¸°
    -0.06
    REFERRED
    -0.06
    ÑĤик
    -0.06
    ÑĦик
    -0.06
     Suche
    -0.06
    _supported
    -0.06
    POSITIVE LOGITS
     female
    0.07
     conversations
    0.07
     conversation
    0.07
    Female
    0.07
    conversation
    0.07
     Conversation
    0.06
     Female
    0.06
    intersect
    0.06
     independent
    0.06
    Conversation
    0.06
    Activations Density 0.001%

    No Known Activations