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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    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. 22
    Prev
    Next
    INDEX
    Explanations

    expressions of personal growth and resilience in the face of adversity

    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
    .dispatcher
    -0.15
    aign
    -0.15
    Úĺ
    -0.14
    idders
    -0.14
    маÑĢ
    -0.14
     Christie
    -0.14
    warts
    -0.13
    cab
    -0.13
    ÙĨÙĪÛĮس
    -0.13
    gabe
    -0.13
    POSITIVE LOGITS
     made
    0.70
    made
    0.60
    Made
    0.56
     Made
    0.56
     MADE
    0.47
    -made
    0.45
    emade
    0.41
     composed
    0.40
     constructed
    0.39
    buat
    0.36
    Activations Density 0.032%

    No Known Activations