© 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. 15167
    Prev
    Next
    INDEX
    Explanations

    numeric values related to performance metrics or statistics

    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
    ../../../
    -0.28
    ../../
    -0.22
    fold
    -0.22
    ../
    -0.21
    ante
    -0.17
    sten
    -0.17
    äºĮäºĮ
    -0.16
    νοÏį
    -0.15
    th
    -0.15
    ingly
    -0.15
    POSITIVE LOGITS
    nd
    0.59
    -thirds
    0.39
    nds
    0.33
    gether
    0.31
    ï¸ı
    0.28
     thirds
    0.27
     dozen
    0.27
    ND
    0.26
     nd
    0.24
    /th
    0.23
    Activations Density 0.206%

    No Known Activations