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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15521
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to formal agreements or documents

    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
    arger
    -0.16
    ئ
    -0.14
    indle
    -0.14
    hattan
    -0.14
    utherford
    -0.14
    amble
    -0.14
    ermann
    -0.14
    paces
    -0.14
    agher
    -0.14
    ลาà¸Ķ
    -0.13
    POSITIVE LOGITS
    ¶ļ
    0.14
    Ì
    0.14
    »
    0.14
     Tay
    0.14
    .LookAndFeel
    0.14
    (/^\
    0.14
    ãĥ¼ãĥ³
    0.13
    ident
    0.13
    amy
    0.13
    clid
    0.13
    Activations Density 0.017%

    No Known Activations