© 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. 30007
    Prev
    Next
    INDEX
    Explanations

    occurrences of arrests and related actions

    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
    adelphia
    -0.16
    slaught
    -0.16
    éĢ¸
    -0.16
    ãĤĩ
    -0.15
    /browse
    -0.15
     Decompiled
    -0.15
    chwitz
    -0.14
    ruc
    -0.14
    à¥įपर
    -0.14
    ¿IJ
    -0.14
    POSITIVE LOGITS
     arrest
    0.81
     arrested
    0.71
     Arrest
    0.71
     arrests
    0.70
     arresting
    0.55
    -ar
    0.48
     appreh
    0.45
    ar
    0.43
    Ar
    0.41
     аÑĢ
    0.40
    Activations Density 0.050%

    No Known Activations