© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 41910
    Prev
    Next
    INDEX
    Explanations

    references to political actions and policies

    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
     eÄŁer
    -0.14
    /as
    -0.14
    adle
    -0.14
    isce
    -0.13
    ï¼īãģ¯
    -0.13
    CHASE
    -0.13
    tadır
    -0.12
    اجات
    -0.12
    argout
    -0.12
    484
    -0.12
    POSITIVE LOGITS
     as
    0.87
     sebagai
    0.58
     как
    0.49
     als
    0.49
     jako
    0.48
     ÏīÏĤ
    0.45
    ä½ľä¸º
    0.44
     Ñıк
    0.39
     каÑĩеÑģÑĤве
    0.38
    为
    0.37
    Activations Density 0.119%

    No Known Activations