© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 24454
    Prev
    Next
    INDEX
    Explanations

    terms related to fees, fines, taxes, and financial charges

    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
    ">//
    -0.16
     escorte
    -0.15
    ascade
    -0.14
    ryn
    -0.14
    οÏģ
    -0.14
    uger
    -0.13
    .CustomButton
    -0.13
    à¹īาส
    -0.13
    ìł¤
    -0.13
    ÑģÑĤин
    -0.13
    POSITIVE LOGITS
     of
    0.66
    of
    0.46
     cá»§a
    0.41
    .of
    0.36
    	of
    0.34
    _of
    0.32
     Of
    0.32
    à¸Ĥà¸Ńà¸ĩ
    0.30
    á»§a
    0.30
    à¹Įà¸Ĥà¸Ńà¸ĩ
    0.30
    Activations Density 0.092%

    No Known Activations