Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 31400
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "U" in various contexts

    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
    надлеж
    -0.17
    волÑı
    -0.16
    olds
    -0.16
    'gc
    -0.16
    utow
    -0.15
    leton
    -0.15
    nst
    -0.15
    รษ
    -0.14
    pies
    -0.14
    ilden
    -0.14
    POSITIVE LOGITS
    gly
    0.20
    asin
    0.20
    å®Ļ
    0.18
    prising
    0.18
    á»ijng
    0.18
    icide
    0.17
    O
    0.17
    gh
    0.17
    fried
    0.16
    trecht
    0.16
    Activations Density 0.197%

    No Known Activations