© 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. 44992
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to societal trends

    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
     quarter
    -0.17
     Quarter
    -0.17
    099
    -0.15
    éĿ
    -0.14
    sworth
    -0.14
     hundred
    -0.14
    Quarter
    -0.14
    ¼åIJĪ
    -0.14
    RuleContext
    -0.14
    ł
    -0.13
    POSITIVE LOGITS
    60
    0.59
    58
    0.58
    61
    0.57
    59
    0.57
    63
    0.56
    55
    0.55
    62
    0.55
    65
    0.55
    64
    0.54
    57
    0.53
    Activations Density 0.090%

    No Known Activations