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. 84
    Prev
    Next
    INDEX
    Explanations

    numerical data related to health assessments and statistical results

    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
    æ°ı
    -0.15
    rung
    -0.15
     Pulse
    -0.15
    udder
    -0.15
     fabric
    -0.14
    æĺŃ
    -0.14
    hung
    -0.14
    ¤ëĭ¤
    -0.14
    alia
    -0.14
    ivid
    -0.14
    POSITIVE LOGITS
    <context
    0.17
    eor
    0.16
    าà¸ĺ
    0.16
     Î
    0.16
    ipop
    0.15
    ellen
    0.15
    elon
    0.15
    agar
    0.15
    xico
    0.14
     Gel
    0.14
    Activations Density 0.046%

    No Known Activations