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. 23344
    Prev
    Next
    INDEX
    Explanations

    details about clothing and accessories

    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
    orney
    -0.16
    รà¸ĵ
    -0.15
    à¸Ļà¸Ħร
    -0.14
    ney
    -0.14
    licit
    -0.14
    ogan
    -0.14
    icket
    -0.14
    owell
    -0.14
    ipi
    -0.13
    ë¹Ī
    -0.13
    POSITIVE LOGITS
     blue
    0.41
     green
    0.38
     white
    0.37
     navy
    0.36
     black
    0.36
     brown
    0.35
     orange
    0.33
     yellow
    0.32
     burg
    0.31
     pale
    0.31
    Activations Density 0.083%

    No Known Activations