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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31408
    Prev
    Next
    INDEX
    Explanations

    aspects related to programming and coding syntax

    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
     fro
    -0.15
     
    -0.15
    ãĥ¼ãĥĪ
    -0.14
     Baldwin
    -0.14
    NSMutableDictionary
    -0.14
     Gregory
    -0.14
     -
    -0.14
    1
    -0.14
     pit
    -0.14
     ref
    -0.14
    POSITIVE LOGITS
    .Sprintf
    0.21
    $MESS
    0.21
     format
    0.19
     Format
    0.18
     str
    0.18
    /format
    0.18
    format
    0.18
     sprintf
    0.17
    sprintf
    0.17
    FormattedMessage
    0.17
    Activations Density 0.028%

    No Known Activations