© 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. 13550
    Prev
    Next
    INDEX
    Explanations

    references to crises and socio-political dynamics related to imperialism and capitalism

    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
    zas
    -0.15
    etsk
    -0.14
     VÅ¡
    -0.14
     pageNo
    -0.14
     завиÑģим
    -0.13
     considering
    -0.13
     Uph
    -0.13
     Tough
    -0.13
     Prev
    -0.13
    ehler
    -0.13
    POSITIVE LOGITS
    oca
    0.17
     imper
    0.16
     rady
    0.15
     increasingly
    0.14
     telesc
    0.14
     cons
    0.13
     FontStyle
    0.13
     decade
    0.13
    iyel
    0.13
    ém
    0.13
    Activations Density 0.487%

    No Known Activations