© 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. 9127
    Prev
    Next
    INDEX
    Explanations

    mentions of tragic accidents and their details

    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
    ylül
    -0.18
     Pistol
    -0.15
    odem
    -0.15
    à¸Ńà¸Ķ
    -0.15
    stad
    -0.15
     Maar
    -0.14
    .debian
    -0.14
    öh
    -0.14
    ylon
    -0.14
    Ctrls
    -0.14
    POSITIVE LOGITS
     pickup
    0.33
     amb
    0.30
     semi
    0.29
     dump
    0.29
     pickups
    0.28
     Hum
    0.28
    amb
    0.27
     pick
    0.27
     van
    0.27
     Semi
    0.27
    Activations Density 0.059%

    No Known Activations