© 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. 8953
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest a call to action or indicate significant statements in discussions of international or social issues

    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
    :http
    -0.18
    -aos
    -0.15
    )(_
    -0.15
    :\\
    -0.14
    etine
    -0.14
    ersed
    -0.14
    )(*
    -0.14
    _("
    -0.14
    ï¿¥
    -0.14
     («
    -0.14
    POSITIVE LOGITS
     [
    0.74
    [s
    0.41
     [↵
    0.29
    ([
    0.29
    [e
    0.28
     [$
    0.27
    _[
    0.25
    [email
    0.24
    [t
    0.24
    -[
    0.24
    Activations Density 0.032%

    No Known Activations