© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41918
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures related to World War II and the Nazi regime

    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
    imos
    -0.19
     Pascal
    -0.15
     nackte
    -0.15
    rå
    -0.15
    uki
    -0.14
    ÄĽt
    -0.14
    aab
    -0.14
    ft
    -0.13
    .Pull
    -0.13
     anarch
    -0.13
    POSITIVE LOGITS
     SS
    0.34
     NS
    0.31
    Hit
    0.28
     Him
    0.27
    NS
    0.26
     Reich
    0.26
     Hit
    0.26
     Hitler
    0.25
     Gest
    0.25
    SS
    0.25
    Activations Density 0.017%

    No Known Activations