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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 63427
    Prev
    Next
    INDEX
    Explanations

    references to target demographics in gaming and media industries

    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
    è
    -0.14
    ante
    -0.13
    .Debugf
    -0.13
     Cyr
    -0.13
    angu
    -0.13
    orf
    -0.12
    çŁ¢
    -0.12
    laden
    -0.12
     Beled
    -0.12
    errick
    -0.12
    POSITIVE LOGITS
     audiences
    0.53
     audience
    0.49
     wider
    0.38
     Audience
    0.36
     widest
    0.33
    aud
    0.32
     broader
    0.31
     wide
    0.29
     viewers
    0.28
     readers
    0.28
    Activations Density 0.125%

    No Known Activations