© 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. 33504
    Prev
    Next
    INDEX
    Explanations

    phrases related to mobile phone usage in suspicious 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
     Sort
    -0.17
    omik
    -0.14
    kowski
    -0.13
    iek
    -0.13
    _ALIAS
    -0.13
    itsu
    -0.13
    ovic
    -0.13
    _unregister
    -0.12
    amba
    -0.12
    uyến
    -0.12
    POSITIVE LOGITS
     what
    0.99
    what
    0.85
     What
    0.62
    What
    0.59
     WHAT
    0.59
     whats
    0.57
    .what
    0.56
    WHAT
    0.51
    ä»Ģä¹Ī
    0.51
     Ø¢ÙĨÚĨÙĩ
    0.48
    Activations Density 0.028%

    No Known Activations