© 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. 25997
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a neutral stance or perspective

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ±
    -0.13
    ļ
    -0.13
    558
    -0.13
     Giang
    -0.13
     CGRectGet
    -0.12
     SolidColorBrush
    -0.12
    ImageData
    -0.12
    ached
    -0.12
    ÑĤен
    -0.12
     Anders
    -0.12
    POSITIVE LOGITS
    0.16
    eneg
    0.15
    ãĤ¤ãĥī
    0.14
    ulp
    0.14
    ieee
    0.13
    luž
    0.13
    istique
    0.13
    âĢİ
    0.12
    ÑĮ
    0.12
     ä¸ĸçķĮ
    0.12
    Activations Density 0.000%

    No Known Activations