© 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. 41884
    Prev
    Next
    INDEX
    Explanations

    themes related to danger and harm in a crowded or emergency context

    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
    Ðĭ
    -0.17
    hausen
    -0.15
    deme
    -0.15
    WithTag
    -0.14
    abric
    -0.14
     TMPro
    -0.13
    trees
    -0.13
    ниÑĤ
    -0.13
     Trees
    -0.13
    SMART
    -0.13
    POSITIVE LOGITS
     stepped
    0.54
     step
    0.53
     tro
    0.50
    step
    0.49
     Step
    0.49
     stepping
    0.48
     tread
    0.46
     tr
    0.45
    Step
    0.45
     STEP
    0.43
    Activations Density 0.028%

    No Known Activations