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. 23130
    Prev
    Next
    INDEX
    Explanations

    concepts related to gender identity and societal norms

    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
    anches
    -0.14
    .EventType
    -0.14
    .MixedReality
    -0.13
    زÙĩ
    -0.13
    CID
    -0.12
    stor
    -0.12
     caracter
    -0.12
    uhan
    -0.12
     Arguments
    -0.12
    ebi
    -0.12
    POSITIVE LOGITS
     norms
    0.33
     expectations
    0.30
     conventional
    0.29
     convention
    0.28
     conventions
    0.28
    norm
    0.27
     expectation
    0.25
     norm
    0.24
     Expect
    0.23
     Convention
    0.23
    Activations Density 0.227%

    No Known Activations