© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8831
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of research studies and their results

    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
     bisher
    -0.13
    reamble
    -0.12
    lah
    -0.12
     saja
    -0.11
    ura
    -0.11
    λά
    -0.11
    URA
    -0.11
    ussen
    -0.11
    ãĢĤæľ¬
    -0.11
    aka
    -0.11
    POSITIVE LOGITS
     another
    1.06
    another
    0.90
     Another
    0.76
    Another
    0.74
    åı¦ä¸Ģ
    0.67
     other
    0.66
     otra
    0.64
     otro
    0.62
    åı¦
    0.62
    åı¦å¤ĸ
    0.57
    Activations Density 0.028%

    No Known Activations