© 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. 42103
    Prev
    Next
    INDEX
    Explanations

    occurrences of significant events related to shooting incidents

    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
    алом
    -0.15
    combe
    -0.14
     {*
    -0.14
     quicker
    -0.14
    bsd
    -0.14
    ECTOR
    -0.14
    EMA
    -0.14
    adel
    -0.13
    æĪ»
    -0.13
    kad
    -0.13
    POSITIVE LOGITS
     ongoing
    0.68
     underway
    0.58
    ongo
    0.54
     happening
    0.53
    æŃ£åľ¨
    0.41
    ngoing
    0.40
     Äijang
    0.40
    ONGO
    0.38
     occurring
    0.38
     being
    0.35
    Activations Density 0.048%

    No Known Activations