© 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. 13793
    Prev
    Next
    INDEX
    Explanations

    instances of social interactions and community engagement

    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
    udit
    -0.17
    ilet
    -0.15
    bject
    -0.15
     ours
    -0.14
    /of
    -0.14
    /from
    -0.14
     everywhere
    -0.13
    aus
    -0.12
    /temp
    -0.12
    æĢ§çļĦ
    -0.12
    POSITIVE LOGITS
     a
    0.34
     an
    0.28
     something
    0.24
     some
    0.21
    ä¸Ģ个
    0.20
     someone
    0.19
    ä¸ĢåĢĭ
    0.18
    something
    0.17
    a
    0.16
    aÄĩ
    0.15
    Activations Density 4.015%

    No Known Activations