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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 63507
    Prev
    Next
    INDEX
    Explanations

    concepts related to national sovereignty and military intervention

    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
     borderTop
    -0.17
     Markup
    -0.15
    agrid
    -0.15
    roman
    -0.15
    overy
    -0.14
    engu
    -0.14
     Keystone
    -0.14
     Wade
    -0.13
     takson
    -0.13
    _FATAL
    -0.13
    POSITIVE LOGITS
     international
    0.26
     UNS
    0.23
     Security
    0.22
    åĽ½éļĽ
    0.22
     INTERNATIONAL
    0.22
    international
    0.21
     diplom
    0.21
    åĽ½éĻħ
    0.21
     interstate
    0.21
     UN
    0.21
    Activations Density 0.040%

    No Known Activations