© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 41643
    Prev
    Next
    INDEX
    Explanations

    references to blog posts and online content

    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
     plá
    -0.15
    lan
    -0.15
    lect
    -0.15
    okit
    -0.15
    zelf
    -0.15
    bs
    -0.14
    bsolute
    -0.14
    à¸ļà¸Ĺ
    -0.14
    lesh
    -0.14
    ÏĦεÏģ
    -0.13
    POSITIVE LOGITS
    graduate
    0.29
    ulate
    0.28
    mort
    0.28
    uring
    0.27
    ulates
    0.26
    cards
    0.25
    greSQL
    0.24
    modern
    0.23
    script
    0.22
    ures
    0.22
    Activations Density 0.035%

    No Known Activations