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. 23353
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future actions or intentions

    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
    fos
    -0.16
    оиÑĤ
    -0.15
    semb
    -0.14
    :n
    -0.14
    ãĥ³ãĥĸ
    -0.14
    lys
    -0.14
    ib
    -0.14
     unable
    -0.14
    retty
    -0.14
    mil
    -0.14
    POSITIVE LOGITS
    'll
    0.37
    ’ll
    0.35
     will
    0.30
    will
    0.27
    ä¼ļ
    0.27
     sẽ
    0.23
    æľĥ
    0.22
     Promise
    0.20
    Will
    0.20
     ä¼ļ
    0.20
    Activations Density 0.024%

    No Known Activations