© 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 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. 14066
    Prev
    Next
    INDEX
    Explanations

    references to academic individuals or institutions in a legal context

    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
    ancel
    -0.19
    ourt
    -0.15
    unt
    -0.14
    inus
    -0.14
    verse
    -0.14
     ont
    -0.14
     Straight
    -0.14
    straight
    -0.14
    fv
    -0.14
    ensi
    -0.14
    POSITIVE LOGITS
     Professor
    0.24
    Professor
    0.23
     Prof
    0.23
    Prof
    0.20
     Ders
    0.20
    prof
    0.19
     professor
    0.19
    .prof
    0.19
     PROF
    0.18
     professors
    0.18
    Activations Density 0.019%

    No Known Activations