© 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. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 14234
    Prev
    Next
    INDEX
    Explanations

    comparisons between genders in professional settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Girl
    -0.23
    Girl
    -0.21
    girl
    -0.20
     granddaughter
    -0.18
     Actress
    -0.18
     daughter
    -0.18
     girl
    -0.17
     Daughter
    -0.17
    daughter
    -0.17
     Kız
    -0.17
    POSITIVE LOGITS
     men
    1.22
     Men
    0.85
    men
    0.79
    Men
    0.78
    -men
    0.77
     males
    0.66
     Männer
    0.64
     MEN
    0.63
     guys
    0.62
    -Men
    0.60
    Activations Density 0.091%

    No Known Activations