© 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. 44622
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and interactions

    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
    ãĤīãģĦ
    -0.17
    jam
    -0.15
    eldorf
    -0.15
    cta
    -0.15
    lav
    -0.14
     overs
    -0.14
     mess
    -0.14
    endi
    -0.14
    ฤ
    -0.14
    imi
    -0.13
    POSITIVE LOGITS
     aside
    0.27
    aside
    0.18
    /us
    0.17
    rrha
    0.17
     into
    0.16
    UpInside
    0.15
    uppe
    0.15
    andering
    0.15
     up
    0.15
    .getBy
    0.14
    Activations Density 0.026%

    No Known Activations