Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23728
    Prev
    Next
    INDEX
    Explanations

    references to societal norms regarding gender roles, particularly in relation to appearance and behavior

    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
    atan
    -0.16
    .construct
    -0.15
     Hlav
    -0.15
     sir
    -0.14
    iegel
    -0.14
    611
    -0.14
    225
    -0.14
    æ´²
    -0.13
    arat
    -0.13
    511
    -0.13
    POSITIVE LOGITS
     superv
    0.19
    rought
    0.16
    ellij
    0.16
    loth
    0.15
    simp
    0.15
     célib
    0.15
     tokens
    0.15
     Straw
    0.15
     simples
    0.14
    disposed
    0.14
    Activations Density 0.049%

    No Known Activations