© 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. 28343
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and court-related terms

    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
     Prosec
    -0.19
     prosecuted
    -0.17
     prosec
    -0.17
     prosecute
    -0.17
    å¾
    -0.17
    Äĥm
    -0.16
    folio
    -0.16
     prosecution
    -0.15
     prosecutions
    -0.15
    ยà¸Ńà¸Ķ
    -0.15
    POSITIVE LOGITS
     judge
    0.52
     Judge
    0.43
    judge
    0.41
     judges
    0.39
     circuit
    0.36
     court
    0.36
    Judge
    0.36
     Circuit
    0.36
     courts
    0.36
     Superior
    0.35
    Activations Density 0.085%

    No Known Activations