© 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 EvalsExportsAPI 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. 22963
    Prev
    Next
    INDEX
    Explanations

    words related to emotional reactions and social issues

    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
     /*↵
    -0.28
    á½±
    -0.25
     à¹Ĩ
    -0.24
    ,)↵
    -0.24
    á½·
    -0.22
     canceled
    -0.22
     percent
    -0.21
     unfavorable
    -0.21
    '></
    -0.21
    ,)
    -0.20
    POSITIVE LOGITS
    ",
    0.41
    ”,
    0.35
    .hpp
    0.35
    ".
    0.32
    ”.
    0.30
    ÙijÙİ
    0.29
    _HPP
    0.27
    ',
    0.27
    ".↵
    0.27
    )",
    0.26
    Activations Density 0.028%

    No Known Activations