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. 31295
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation marks and some formatting elements

    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
    the
    -0.20
    ↵
    -0.18
    â̦
    -0.17
    :
    -0.16
    **
    -0.15
    ...↵
    -0.15
     bot
    -0.14
    Kay
    -0.14
    Bot
    -0.14
     irre
    -0.14
    POSITIVE LOGITS
    sian
    0.16
    ê·
    0.16
    lus
    0.16
    eny
    0.15
    UILTIN
    0.15
    ando
    0.14
    Spinner
    0.14
    aternion
    0.14
    eniable
    0.14
    (çģ«
    0.14
    Activations Density 0.039%

    No Known Activations