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. 23220
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it" and variations or phrases closely associated with it

    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
    ses
    -0.18
     –
    -0.17
     --
    -0.17
    ÑĮко
    -0.17
    ÑĥÑĤи
    -0.16
    βολ
    -0.15
    yms
    -0.15
    eyh
    -0.15
    yect
    -0.15
    ην
    -0.14
    POSITIVE LOGITS
    ir
    0.31
    atre
    0.30
    gether
    0.30
    bsites
    0.25
    adays
    0.25
    xiety
    0.24
    ftware
    0.24
    bidden
    0.24
    /-
    0.23
    ctrine
    0.21
    Activations Density 0.147%

    No Known Activations