© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 44906
    Prev
    Next
    INDEX
    Explanations

    data related to statistical values and comparisons

    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
    3
    -0.20
     Three
    -0.20
     three
    -0.19
    ä¸īå¹´
    -0.19
     THREE
    -0.18
    Three
    -0.17
    ï¼ĵ
    -0.17
    03
    -0.17
     Four
    -0.17
     four
    -0.17
    POSITIVE LOGITS
    10
    0.36
    8
    0.29
    9
    0.29
    11
    0.28
    7
    0.26
    12
    0.25
     tenth
    0.23
     ten
    0.23
    оÑģÑĮ
    0.23
    åįģ
    0.23
    Activations Density 0.032%

    No Known Activations