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. 23445
    Prev
    Next
    INDEX
    Explanations

    key terms related to trade and economic exchanges

    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
    ppv
    -0.17
     ÐĿаÑģеленнÑı
    -0.16
    ITAL
    -0.15
    ------+------+
    -0.15
    TokenType
    -0.14
    IGNAL
    -0.14
    .statusStrip
    -0.14
    mour
    -0.14
    QRST
    -0.14
    ·æĸ°
    -0.14
    POSITIVE LOGITS
     official
    0.15
    at
    0.14
    al
    0.14
    ain
    0.13
    åħ·ä½ĵ
    0.13
     hereby
    0.13
    kol
    0.13
     typical
    0.13
    do
    0.13
    lb
    0.13
    Activations Density 0.005%

    No Known Activations