© 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. 13213
    Prev
    Next
    INDEX
    Explanations

    references to theories related to societal evolution and policy implications

    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
     consc
    -0.17
    beck
    -0.16
    zan
    -0.15
     justify
    -0.14
    ldkf
    -0.14
     Techniques
    -0.14
    ovit
    -0.13
    ÑĤÑĢо
    -0.13
    legen
    -0.13
    izza
    -0.13
    POSITIVE LOGITS
     view
    0.35
     account
    0.30
     views
    0.28
    view
    0.26
     understanding
    0.24
     conception
    0.24
     position
    0.23
     notion
    0.23
     View
    0.23
     Account
    0.22
    Activations Density 0.076%

    No Known Activations