© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 63536
    Prev
    Next
    INDEX
    Explanations

    references to specific card game mechanics and strategies

    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
    lew
    -0.14
    ãĥªãĤ¢
    -0.13
    iddi
    -0.13
    ãĥĭãĤ¢
    -0.13
    ãģŁãĤī
    -0.12
    dea
    -0.12
    ieves
    -0.12
    AndWait
    -0.12
    ãĢĤãĢĤ↵↵
    -0.12
     Herb
    -0.12
    POSITIVE LOGITS
    ̣
    0.14
    Solar
    0.13
     infer
    0.13
    ŀ
    0.13
    ustos
    0.13
    ajaran
    0.13
    osis
    0.13
    _fonts
    0.13
     Demir
    0.13
    allocator
    0.13
    Activations Density 0.051%

    No Known Activations