© 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. 21652
    Prev
    Next
    INDEX
    Explanations

    references to Polish culture and societal issues

    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
     zbyt
    -0.19
    LayoutConstraint
    -0.17
    riz
    -0.15
    ÙĪÙĨØ©
    -0.15
     vÃŃde
    -0.15
     öden
    -0.15
     fetisch
    -0.15
     pump
    -0.14
    üss
    -0.14
     prostitut
    -0.14
    POSITIVE LOGITS
     Polish
    0.74
     Poland
    0.69
     polish
    0.66
     Warsaw
    0.57
    Pol
    0.53
     Pols
    0.48
     Krak
    0.48
     ÐŁÐ¾Ð»ÑĮ
    0.47
     полÑĮ
    0.46
    Wars
    0.42
    Activations Density 0.049%

    No Known Activations