© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 21252
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the importance of discussing truth and factual statements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    buah
    -0.14
     giác
    -0.14
    phe
    -0.14
    oplevel
    -0.14
    ầ
    -0.13
    tml
    -0.13
    .sax
    -0.13
    :async
    -0.13
    lica
    -0.13
    pies
    -0.13
    POSITIVE LOGITS
     sir
    0.64
     Sir
    0.52
    Sir
    0.50
     dear
    0.47
     Dear
    0.39
     gentlemen
    0.39
    Dear
    0.34
     mate
    0.33
     amigo
    0.31
     darling
    0.31
    Activations Density 0.020%

    No Known Activations