© 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. 24829
    Prev
    Next
    INDEX
    Explanations

    references to individuals with the surname "Jablonski" and related variations in the context of the CIA

    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
     contro
    -0.15
    ore
    -0.15
    βε
    -0.14
     Sext
    -0.14
     bist
    -0.14
    avel
    -0.14
    arus
    -0.14
    ãĥĸãĥ«
    -0.14
    ecc
    -0.14
    aty
    -0.14
    POSITIVE LOGITS
    ilty
    0.17
    kker
    0.16
    itung
    0.15
    olute
    0.15
    uary
    0.15
    querque
    0.15
     Minute
    0.14
    atorium
    0.14
    istencia
    0.14
    ssi
    0.14
    Activations Density 0.014%

    No Known Activations