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

    Neuronpedia

    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. 28458
    Prev
    Next
    INDEX
    Explanations

    statements that report or reveal statistics and findings, particularly related to gender

    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
    lesia
    -0.14
    etooth
    -0.14
    iew
    -0.14
    acional
    -0.14
    .nano
    -0.14
    __[
    -0.14
     Seam
    -0.14
    usercontent
    -0.14
    ponsive
    -0.13
    /cache
    -0.13
    POSITIVE LOGITS
     alarm
    0.38
     worrying
    0.32
     alarming
    0.32
    Alarm
    0.30
     Alarm
    0.30
     distress
    0.30
     disturbing
    0.30
     sober
    0.29
     concerning
    0.28
     sad
    0.28
    Activations Density 0.245%

    No Known Activations