© 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. 12789
    Prev
    Next
    INDEX
    Explanations

    phrases indicating lists or rankings

    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
    estre
    -0.17
    rosso
    -0.14
     recht
    -0.13
    ORY
    -0.13
    æĬ¬
    -0.13
    consin
    -0.13
    oka
    -0.13
     outnumber
    -0.13
    IGHL
    -0.13
    EST
    -0.13
    POSITIVE LOGITS
     top
    1.22
     Top
    1.06
    Top
    0.96
    top
    0.95
    -top
    0.88
    _top
    0.83
     TOP
    0.83
    (top
    0.77
    .top
    0.76
    /top
    0.75
    Activations Density 0.037%

    No Known Activations