© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 25245
    Prev
    Next
    INDEX
    Explanations

    references to secret societies and their associated leadership

    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
    iev
    -0.14
    eroon
    -0.14
    主任
    -0.14
     èĩªåĬ¨çĶŁæĪIJ
    -0.14
    omaly
    -0.14
    _UART
    -0.13
    èn
    -0.13
     Äijình
    -0.13
    rowsable
    -0.13
    à¸Ĭà¸Ļะ
    -0.13
    POSITIVE LOGITS
     Init
    0.60
     initi
    0.59
     initiation
    0.58
     Initi
    0.57
    init
    0.55
    Init
    0.53
     initiate
    0.53
     initiated
    0.52
    -init
    0.49
     init
    0.48
    Activations Density 0.030%

    No Known Activations