© 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 EvalsExportsinterp-engineNEWAPI 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. 25218
    Prev
    Next
    INDEX
    Explanations

    references to internal or domestic political matters related to China

    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
    TF
    -0.15
    oda
    -0.14
    ulk
    -0.13
     Abram
    -0.13
    uta
    -0.12
    ILT
    -0.12
    ubi
    -0.12
    /address
    -0.12
    нем
    -0.12
    æ´¥
    -0.12
    POSITIVE LOGITS
     affairs
    0.97
     Affairs
    0.88
     affair
    0.81
    aff
    0.81
    Aff
    0.79
     Aff
    0.75
     aff
    0.75
    -aff
    0.69
    _aff
    0.65
     AFF
    0.63
    Activations Density 0.022%

    No Known Activations