© 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. 44660
    Prev
    Next
    INDEX
    Explanations

    discussions around privilege and social justice 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
    atak
    -0.14
    irement
    -0.14
    à¸Ļà¸Ķ
    -0.13
     irrational
    -0.13
    訳
    -0.13
    bench
    -0.13
    owi
    -0.13
     عاÙħÙĦ
    -0.13
    à¹ģà¸ľ
    -0.13
    ÑĥлÑİ
    -0.13
    POSITIVE LOGITS
     intersection
    0.30
     privilege
    0.29
     Intersection
    0.28
    intersection
    0.27
    Intersection
    0.25
     white
    0.23
     privileged
    0.23
     ally
    0.23
     intersections
    0.23
     dismant
    0.22
    Activations Density 0.123%

    No Known Activations