© 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. 21179
    Prev
    Next
    INDEX
    Explanations

    occurrences of the character "Dur" and its variations, likely indicating a focus on dates or events related to "Durin."

    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
    wrap
    -0.15
    lung
    -0.14
    weise
    -0.14
     ==============================================================
    -0.14
    ooled
    -0.14
    nid
    -0.14
    íĸ¥
    -0.14
    lamp
    -0.14
     ëĭ¤
    -0.14
    ularity
    -0.14
    POSITIVE LOGITS
     Dur
    0.21
     dur
    0.19
    ango
    0.19
    dur
    0.18
    üst
    0.17
    umd
    0.17
    -lasting
    0.17
    Dur
    0.17
    ham
    0.17
     lasting
    0.17
    Activations Density 0.008%

    No Known Activations