© 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. 42047
    Prev
    Next
    INDEX
    Explanations

    instances of the word "case" and its variations

    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
    輪
    -0.15
    uters
    -0.15
    esz
    -0.15
    abar
    -0.15
    alian
    -0.14
    jit
    -0.14
    akin
    -0.14
    ots
    -0.13
    alia
    -0.13
    itol
    -0.13
    POSITIVE LOGITS
     with
    0.25
     for
    0.25
     chez
    0.23
    สำหร
    0.19
     everywhere
    0.18
     regarding
    0.18
     whenever
    0.18
    对äºİ
    0.18
     here
    0.17
     true
    0.17
    Activations Density 0.070%

    No Known Activations