© 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. 14500
    Prev
    Next
    INDEX
    Explanations

    themes of exclusion and identity

    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
    ãģĵãĤĵãģª
    -0.18
    oload
    -0.17
    abela
    -0.15
    .chomp
    -0.15
    \Mapping
    -0.14
    è¿Ļä¹Ī
    -0.14
    ãģĿãĤĵãģª
    -0.14
     ÑģлÑĭÑĪ
    -0.14
     lesb
    -0.14
     повин
    -0.14
    POSITIVE LOGITS
     truly
    0.35
     fully
    0.33
     entirely
    0.30
     really
    0.30
     ever
    0.28
     completely
    0.28
    å®Įåħ¨
    0.26
    really
    0.25
     Truly
    0.25
    Really
    0.24
    Activations Density 0.064%

    No Known Activations