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. 23671
    Prev
    Next
    INDEX
    Explanations

    code snippets related to HTML elements and their properties in a programming 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
    íĭ´
    -0.14
    )++;↵
    -0.14
     konkrét
    -0.14
    .Apis
    -0.13
    åij½
    -0.13
    __':↵
    -0.13
    .foreach
    -0.13
    .*
    -0.13
    ÏĢοι
    -0.13
    .bunifuFlatButton
    -0.13
    POSITIVE LOGITS
     +
    0.22
     replacement
    0.16
    .toString
    0.16
     replacements
    0.16
     toString
    0.15
    หà¸Ļ
    0.15
     replace
    0.15
     ?:
    0.15
    еко
    0.14
    ulus
    0.14
    Activations Density 0.031%

    No Known Activations