© 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. 28852
    Prev
    Next
    INDEX
    Explanations

    specific phrases and terms related to legal proceedings and trials

    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
    ntl
    -0.17
    illard
    -0.15
    ิย
    -0.15
    isel
    -0.15
    одÑĭ
    -0.14
    ands
    -0.14
    NTAX
    -0.14
    BackPressed
    -0.14
    Ĥæķ°
    -0.14
    æľį
    -0.14
    POSITIVE LOGITS
     concerns
    0.38
     concern
    0.33
     pert
    0.33
     centers
    0.33
     concerned
    0.32
     deals
    0.32
     deal
    0.30
     Deal
    0.30
     center
    0.30
     centres
    0.29
    Activations Density 0.050%

    No Known Activations