© 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. 33314
    Prev
    Next
    INDEX
    Explanations

    phrases related to investigations and legal proceedings

    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
     Bench
    -0.18
     Insight
    -0.15
    ÐłÐĿ
    -0.14
     Insights
    -0.13
     Sne
    -0.13
    andi
    -0.13
    lub
    -0.13
    kre
    -0.13
     bench
    -0.12
    ãĤ¯ãĤ»
    -0.12
    POSITIVE LOGITS
     investigation
    0.58
     investigations
    0.50
    invest
    0.48
     Investigation
    0.47
     Investigations
    0.42
     investigate
    0.40
    Invest
    0.40
     investigating
    0.38
     investigated
    0.38
     invest
    0.38
    Activations Density 0.129%

    No Known Activations