Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23461
    Prev
    Next
    INDEX
    Explanations

    references to religious texts and figures

    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
    stantiate
    -0.16
    odus
    -0.15
    azen
    -0.15
    exter
    -0.15
    ovah
    -0.15
    ERRU
    -0.14
    sterol
    -0.14
     ÙĨÙħ
    -0.14
    OMUX
    -0.14
    stadt
    -0.14
    POSITIVE LOGITS
     Gal
    0.38
     Paul
    0.37
    Paul
    0.33
     Romans
    0.31
    Gal
    0.31
     Corinth
    0.30
     Rom
    0.28
     Col
    0.28
     paul
    0.28
    Rom
    0.28
    Activations Density 0.007%

    No Known Activations