© 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. 33401
    Prev
    Next
    INDEX
    Explanations

    mentions of government policies related to security, civil liberties, and anti-terrorism measures

    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
    acerb
    -0.17
     Tune
    -0.15
    uits
    -0.15
     Coast
    -0.15
     èģ
    -0.15
    ibold
    -0.15
    idel
    -0.15
    oss
    -0.15
    ekler
    -0.14
    .testng
    -0.14
    POSITIVE LOGITS
     British
    0.32
     UK
    0.31
     MI
    0.29
     Britain
    0.29
    UK
    0.28
    MI
    0.27
     Brit
    0.26
    British
    0.26
     british
    0.24
     brit
    0.23
    Activations Density 0.068%

    No Known Activations