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. 23419
    Prev
    Next
    INDEX
    Explanations

    references to team performance and changes in sports management

    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
    terminal
    -0.15
    StreamReader
    -0.15
    ERN
    -0.14
    omo
    -0.14
    pery
    -0.14
    aab
    -0.14
    errer
    -0.14
    ÑĢоÑĤив
    -0.13
    blr
    -0.13
    tech
    -0.13
    POSITIVE LOGITS
     offseason
    0.48
     off
    0.47
     Off
    0.40
    off
    0.36
    Off
    0.34
    -off
    0.31
    .off
    0.31
    _off
    0.30
    (off
    0.30
     summer
    0.28
    Activations Density 0.031%

    No Known Activations