© 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. 28386
    Prev
    Next
    INDEX
    Explanations

    discussions around gender roles and stereotypes

    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
    presso
    -0.16
     пÑĢидеÑĤÑģÑı
    -0.15
    otal
    -0.15
    avra
    -0.15
    _EXISTS
    -0.14
    isha
    -0.14
    RLF
    -0.14
    CRET
    -0.14
    kil
    -0.14
    á»ĵi
    -0.14
    POSITIVE LOGITS
     supposed
    1.18
     suppose
    0.95
     meant
    0.71
     Suppose
    0.55
     SUP
    0.53
     supposedly
    0.50
    sup
    0.48
     alleged
    0.47
     Sup
    0.47
     intended
    0.46
    Activations Density 0.057%

    No Known Activations