Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 15847
    Prev
    Next
    INDEX
    Explanations

    references to traffic regulations and safety measures

    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
    vat
    -0.15
     firing
    -0.15
    rift
    -0.14
    γÏĮ
    -0.14
     cánh
    -0.13
     ranges
    -0.13
     Frontier
    -0.13
    SKI
    -0.13
     vat
    -0.13
    \Container
    -0.13
    POSITIVE LOGITS
     traffic
    0.39
     Traffic
    0.36
    traffic
    0.32
    Traffic
    0.31
     pedestrian
    0.30
     safety
    0.28
     pedestrians
    0.26
     street
    0.25
     Safety
    0.25
     traff
    0.25
    Activations Density 0.054%

    No Known Activations