© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8523
    Prev
    Next
    INDEX
    Explanations

    occurrences of significant actions and changes, particularly in the context of acquisition and collaboration

    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
    ãĥĢ
    -0.20
    è¾¾
    -0.19
     prostituer
    -0.16
    doll
    -0.14
     Dispatch
    -0.14
    Disp
    -0.14
     Disp
    -0.14
     ãĥĢ
    -0.14
    dash
    -0.14
    dos
    -0.14
    POSITIVE LOGITS
    -de
    0.84
     DE
    0.82
    de
    0.76
     De
    0.75
    De
    0.75
    _de
    0.74
    .de
    0.69
    (de
    0.68
    /de
    0.68
     de
    0.65
    Activations Density 0.018%

    No Known Activations