© 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. 33284
    Prev
    Next
    INDEX
    Explanations

    instances of statistical or numerical data presented in a structured format

    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
    500
    -0.18
    400
    -0.17
    300
    -0.16
    ebo
    -0.15
    800
    -0.15
    edik
    -0.14
    aby
    -0.14
    vig
    -0.14
    700
    -0.14
    100
    -0.14
    POSITIVE LOGITS
    assis
    0.17
    TestCategory
    0.16
    LOAT
    0.14
    NTAX
    0.14
    ranÃŃ
    0.14
    ickers
    0.14
    ILLISE
    0.14
    .opensource
    0.14
    ÏĦοι
    0.14
    گاÙĩÛĮ
    0.13
    Activations Density 0.218%

    No Known Activations