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. 9332
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to sports events

    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
     ÑĤоÑīо
    -0.16
     právÄĽ
    -0.15
    INCLUDED
    -0.14
     jinak
    -0.14
    HECK
    -0.14
    ONGL
    -0.13
     INTERRUPTION
    -0.13
    ERNEL
    -0.13
     tÅĻeba
    -0.13
    ATAR
    -0.13
    POSITIVE LOGITS
     :)
    0.14
    :↵
    0.13
    rray
    0.13
      
    0.12
    ceae
    0.12
     in
    0.12
     :-)
    0.12
     kidding
    0.12
     
    0.12
    :</
    0.12
    Activations Density 26.854%

    No Known Activations