© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24982
    Prev
    Next
    INDEX
    Explanations

    terms related to illegal activities and suspicious behavior

    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
    ạ
    -0.16
    бин
    -0.14
    unning
    -0.14
    solete
    -0.14
    oko
    -0.13
    alet
    -0.13
    anches
    -0.13
    à¹Ģà¸Ħราะห
    -0.13
    endar
    -0.13
    ainment
    -0.13
    POSITIVE LOGITS
     suspect
    0.73
     suspicious
    0.67
     Sus
    0.63
     suspicion
    0.62
     suspects
    0.61
     Susp
    0.60
    sus
    0.58
     suspected
    0.58
     suspicions
    0.58
     sus
    0.57
    Activations Density 0.079%

    No Known Activations