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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 44365
    Prev
    Next
    INDEX
    Explanations

    terms related to evaluation and analysis of information

    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
    ataires
    -0.14
     McKenzie
    -0.14
    olved
    -0.13
     ÙĪرز
    -0.13
     traps
    -0.13
    vatel
    -0.13
    lep
    -0.13
    -spe
    -0.13
    ฯ
    -0.12
    Ñħови
    -0.12
    POSITIVE LOGITS
     of
    0.47
     của
    0.25
    of
    0.23
    à¸Ĥà¸Ńà¸ĩ
    0.20
     ÏĦÏīν
    0.20
    à¹Įà¸Ĥà¸Ńà¸ĩ
    0.20
     how
    0.20
    	of
    0.19
     ÏĦηÏĤ
    0.19
    nof
    0.19
    Activations Density 0.148%

    No Known Activations