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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21769
    Prev
    Next
    INDEX
    Explanations

    references to governmental roles and influences

    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
    ampo
    -0.17
    UT
    -0.14
    etik
    -0.13
     nạn
    -0.13
    ÄĻd
    -0.13
    /antlr
    -0.13
    ady
    -0.13
    engu
    -0.13
    hiba
    -0.13
    uko
    -0.12
    POSITIVE LOGITS
     government
    0.90
     Government
    0.74
    government
    0.74
    æĶ¿åºľ
    0.71
    -government
    0.69
    Government
    0.68
     governments
    0.66
     governmental
    0.59
     governo
    0.56
     Governments
    0.55
    Activations Density 0.070%

    No Known Activations