© 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 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. 85504
    Prev
    Next
    INDEX
    Explanations

    references to gender identity and representation

    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
    ofilm
    -0.07
    ongyang
    -0.07
    lier
    -0.07
    iken
    -0.07
    opak
    -0.07
    enas
    -0.07
    utex
    -0.07
    airo
    -0.07
    actus
    -0.07
    รà¸ģ
    -0.07
    POSITIVE LOGITS
     neither
    0.07
     fluid
    0.07
     vag
    0.07
     gender
    0.07
     trans
    0.06
     neutral
    0.06
     genders
    0.06
    æ´
    0.06
    fluid
    0.06
     mü
    0.06
    Activations Density 0.012%

    No Known Activations