© 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. 12518
    Prev
    Next
    INDEX
    Explanations

    references to usernames or identifiers related to online activities or communities

    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
    âĸį
    -0.15
    á»IJ
    -0.15
    abbo
    -0.14
    ,:,
    -0.14
    roys
    -0.14
    legg
    -0.14
    ycin
    -0.14
    ICO
    -0.14
    agraph
    -0.14
    alah
    -0.14
    POSITIVE LOGITS
    97
    0.23
    123
    0.22
    200
    0.22
    23
    0.22
    69
    0.21
    77
    0.21
    96
    0.21
    85
    0.21
    89
    0.21
    75
    0.20
    Activations Density 0.073%

    No Known Activations