© 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. 63579
    Prev
    Next
    INDEX
    Explanations

    references to incidents involving hacking and cybersecurity concerns

    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
    infeld
    -0.15
     Tin
    -0.15
    odesk
    -0.14
    wayne
    -0.14
     saf
    -0.14
    WXYZ
    -0.14
    ä¸ĭ载次æķ°
    -0.13
    <"
    -0.13
    γά
    -0.13
     Bihar
    -0.13
    POSITIVE LOGITS
     Korean
    0.76
     Korea
    0.76
     Seoul
    0.69
     Koreans
    0.65
     South
    0.59
    South
    0.51
     HÃłn
    0.48
     Kore
    0.46
    飩
    0.46
    éŁĵ
    0.45
    Activations Density 0.049%

    No Known Activations