© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 45187
    Prev
    Next
    INDEX
    Explanations

    inquiries and requests for information

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    insk
    -0.17
    inski
    -0.15
    ÑģÑĤÑĢи
    -0.14
    ãģļ
    -0.14
    ogn
    -0.14
    ackle
    -0.13
    OfYear
    -0.13
    redo
    -0.13
    ãģ°ãģĭãĤĬ
    -0.13
    Ÿ
    -0.13
    POSITIVE LOGITS
     questions
    0.46
     Questions
    0.36
    questions
    0.33
     question
    0.33
     suggestions
    0.29
     queries
    0.29
     concerns
    0.28
    Questions
    0.28
    _questions
    0.25
     QUEST
    0.25
    Activations Density 0.057%

    No Known Activations