© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 32947
    Prev
    Next
    INDEX
    Explanations

    references to nuclear-related contexts and locations

    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
    arine
    -0.14
    qus
    -0.14
     Bradley
    -0.14
    cdn
    -0.14
    ζα
    -0.14
     fon
    -0.13
    èī
    -0.13
    Ø´ÙħاÙĦÛĮ
    -0.13
     toc
    -0.13
    åłĤ
    -0.13
    POSITIVE LOGITS
    ̧
    0.14
     rural
    0.14
    /Area
    0.14
     Bik
    0.14
     remote
    0.14
    aec
    0.13
    asn
    0.13
    pch
    0.13
     ÙĨزد
    0.13
    esome
    0.13
    Activations Density 0.031%

    No Known Activations