© 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. 43332
    Prev
    Next
    INDEX
    Explanations

    references to individuals in the context of gender discussions

    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
    siyon
    -0.15
    /goto
    -0.15
    $MESS
    -0.14
    ãĥ³ãĤ¬
    -0.14
    deaux
    -0.14
    ibo
    -0.14
    gable
    -0.14
    biên
    -0.14
    nel
    -0.14
    nal
    -0.13
    POSITIVE LOGITS
    /her
    0.57
    /she
    0.52
     or
    0.41
    .her
    0.35
     her
    0.33
    her
    0.31
     hers
    0.30
     she
    0.29
    æĪĸ
    0.28
     Her
    0.27
    Activations Density 0.049%

    No Known Activations