© 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. 22163
    Prev
    Next
    INDEX
    Explanations

    technical terms related to variable and data management in programming

    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
    SG
    -0.21
    an
    -0.20
    ap
    -0.17
    p
    -0.16
    in
    -0.16
    anth
    -0.16
    aney
    -0.16
    âĶģâĶģ
    -0.15
    axy
    -0.15
    b
    -0.15
    POSITIVE LOGITS
    azing
    0.16
    ules
    0.15
    à¸Ĭาà¸ķ
    0.15
    nest
    0.15
    ÑħÑĥ
    0.15
    ERICAN
    0.14
    ee
    0.14
    eting
    0.14
    eller
    0.14
    eyer
    0.14
    Activations Density 0.055%

    No Known Activations