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. 23501
    Prev
    Next
    INDEX
    Explanations

    brand names and products related to retail or consumer goods

    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
    ordion
    -0.14
    ÏĦιÏĥ
    -0.14
    )))),
    -0.14
    auss
    -0.14
    jian
    -0.14
    furt
    -0.14
    _cpp
    -0.14
    lius
    -0.13
    aneous
    -0.13
    Mage
    -0.13
    POSITIVE LOGITS
    _nh
    0.15
     âĹĦ
    0.15
    asil
    0.15
    iva
    0.14
    _isr
    0.14
    ılıç
    0.14
     portfolio
    0.14
    -Mart
    0.14
    forman
    0.14
    obox
    0.14
    Activations Density 0.040%

    No Known Activations