© 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. 43124
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or strong emotion

    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
     darn
    -0.16
    emez
    -0.15
    inos
    -0.15
    á»ĩu
    -0.14
     #__
    -0.14
     terribly
    -0.14
    patial
    -0.14
    ilities
    -0.14
     ìĹĦ
    -0.14
    anke
    -0.14
    POSITIVE LOGITS
     fuck
    0.58
    fuck
    0.55
     fucking
    0.54
     fucks
    0.51
     Fuck
    0.51
    Fuck
    0.51
     mother
    0.48
     Fucking
    0.48
     FUCK
    0.48
     fucked
    0.46
    Activations Density 0.025%

    No Known Activations