© 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. 25421
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and activism

    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
     something
    -0.27
     things
    -0.24
     stuff
    -0.23
     thing
    -0.20
    something
    -0.19
     kind
    -0.18
     kinds
    -0.18
     another
    -0.18
     Something
    -0.17
     really
    -0.17
    POSITIVE LOGITS
     respective
    0.20
     respectively
    0.16
    /by
    0.15
    addtogroup
    0.14
     individuals
    0.14
     Individuals
    0.14
    leftright
    0.14
    à¸Ĥà¸Ńà¸ĩà¸ľ
    0.14
    necessary
    0.13
    ìĶĢ
    0.13
    Activations Density 0.034%

    No Known Activations