© 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. 28306
    Prev
    Next
    INDEX
    Explanations

    conjunctions and comparative phrases relating to gender issues

    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
     men
    -0.39
     Men
    -0.30
    Men
    -0.28
    çĶ·äºº
    -0.28
     Männer
    -0.27
     boys
    -0.27
    -men
    -0.26
     Boys
    -0.25
    çĶ·åŃIJ
    -0.24
     Guys
    -0.23
    POSITIVE LOGITS
     female
    0.57
     Female
    0.52
    Female
    0.51
    female
    0.49
    emale
    0.39
    _female
    0.35
     females
    0.33
    EMALE
    0.33
    -f
    0.30
     Male
    0.29
    Activations Density 0.009%

    No Known Activations