© 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. 15551
    Prev
    Next
    INDEX
    Explanations

    expressions of fear and self-reflection

    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
     ours
    -0.32
     we
    -0.28
     ourselves
    -0.23
    we
    -0.22
     our
    -0.20
    We
    -0.20
    æĪij们
    -0.19
    ours
    -0.19
     theirs
    -0.18
     their
    -0.18
    POSITIVE LOGITS
    à¸ľà¸¡
    0.22
     fucks
    0.18
     myself
    0.18
    让æĪij
    0.18
    俺ãģ¯
    0.17
     my
    0.17
    .scalablytyped
    0.17
     Fucked
    0.16
     minha
    0.16
     life
    0.16
    Activations Density 0.075%

    No Known Activations