© 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. 15443
    Prev
    Next
    INDEX
    Explanations

    references to legislation, governance, and legal procedures

    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
    otto
    -0.15
    utsch
    -0.15
    .Formatter
    -0.15
    .EventQueue
    -0.14
    OMIC
    -0.14
    lyph
    -0.14
    ħ§
    -0.14
     подв
    -0.14
    aits
    -0.14
    AIT
    -0.14
    POSITIVE LOGITS
     determined
    0.75
     determination
    0.70
     determines
    0.62
     determine
    0.62
     Determin
    0.61
     determin
    0.60
     determining
    0.59
    Determin
    0.52
     Determine
    0.49
     Determines
    0.47
    Activations Density 0.050%

    No Known Activations