© 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. 15132
    Prev
    Next
    INDEX
    Explanations

    references to design-related issues and their impacts

    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
     &&↵
    -0.17
    —and
    -0.15
    AndGet
    -0.14
    ạt
    -0.13
    _EXTERN
    -0.13
    à¹Īà¸Ńย
    -0.12
    MF
    -0.12
    åij¢
    -0.12
    ách
    -0.12
    ÏĥÏĦά
    -0.12
    POSITIVE LOGITS
     or
    0.82
     æĪĸ
    0.64
     или
    0.64
     oder
    0.62
     atau
    0.59
    æĪĸèĢħ
    0.58
    æĪĸ
    0.57
    ï¼ĮæĪĸ
    0.56
     nebo
    0.56
     หร
    0.54
    Activations Density 0.193%

    No Known Activations