© 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. 24857
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with color codes and image processing parameters

    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
     otherwise
    -0.15
    sik
    -0.15
    ably
    -0.14
    sert
    -0.14
    cribe
    -0.14
    eds
    -0.14
    entieth
    -0.14
    .googlecode
    -0.14
    immer
    -0.14
    æķı
    -0.13
    POSITIVE LOGITS
    000
    0.26
    001
    0.19
    Û°Û°Û°
    0.18
    uze
    0.17
    004
    0.15
    ±ä¹IJ
    0.15
    006
    0.15
    cip
    0.15
     Propel
    0.15
    005
    0.15
    Activations Density 0.015%

    No Known Activations