© 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 EvalsExportsAPI 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. 43141
    Prev
    Next
    INDEX
    Explanations

    the mention of parentheses and references to articles or sections of text

    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
    dcc
    -0.15
    xfd
    -0.14
    xfc
    -0.14
    afc
    -0.14
    xcf
    -0.13
    ffd
    -0.13
    xFC
    -0.13
    γη
    -0.13
    xDD
    -0.13
    /DD
    -0.13
    POSITIVE LOGITS
     EB
    0.57
    EB
    0.54
     IB
    0.53
     SB
    0.51
    IB
    0.51
    SB
    0.50
     RB
    0.48
     LB
    0.47
     PB
    0.46
     MB
    0.46
    Activations Density 0.018%

    No Known Activations