© 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. 33609
    Prev
    Next
    INDEX
    Explanations

    terms related to illegal activities, particularly regarding immigration and other unlawful behaviors

    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
    /Gate
    -0.15
    rey
    -0.15
    BYTES
    -0.14
    ãģıãĤĭ
    -0.14
    ÄĽtÅ¡
    -0.14
    urge
    -0.14
    ราà¸Ħ
    -0.14
    íĴ
    -0.14
    getting
    -0.14
    iller
    -0.13
    POSITIVE LOGITS
    ities
    0.33
    /il
    0.28
    ized
    0.22
    /un
    0.22
    ITIES
    0.20
     immigrants
    0.20
    iti
    0.18
    ely
    0.18
     aliens
    0.18
    istic
    0.18
    Activations Density 0.025%

    No Known Activations