© 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. 24221
    Prev
    Next
    INDEX
    Explanations

    discussions related to media and communication contexts

    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
    аÑĢов
    -0.15
    isci
    -0.15
     ><?
    -0.14
    ForSegue
    -0.13
    META
    -0.13
     ank
    -0.13
    à¹Ĥล
    -0.13
     inward
    -0.12
    [of
    -0.12
    üt
    -0.12
    POSITIVE LOGITS
     elsewhere
    0.48
     in
    0.42
     on
    0.34
     at
    0.31
     throughout
    0.28
     within
    0.28
    åľ¨
    0.26
    else
    0.26
     trong
    0.25
     chez
    0.25
    Activations Density 0.127%

    No Known Activations