© 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. 28876
    Prev
    Next
    INDEX
    Explanations

    concepts related to spiritual practices and experiences

    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
    iek
    -0.14
    ombine
    -0.14
    adle
    -0.14
    [--
    -0.14
    zew
    -0.14
    úng
    -0.14
     ÑģкÑĢÑĭ
    -0.14
     infect
    -0.14
    .isHidden
    -0.13
    iks
    -0.13
    POSITIVE LOGITS
     experiences
    0.26
     experience
    0.25
     states
    0.23
     Experience
    0.21
    plevel
    0.21
     experi
    0.20
     altered
    0.20
    experience
    0.19
    states
    0.19
    -states
    0.19
    Activations Density 0.096%

    No Known Activations