© 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 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. 14456
    Prev
    Next
    INDEX
    Explanations

    connections related to cultural constructs and their 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
    issen
    -0.17
    .scalablytyped
    -0.17
    ÑģÑĤика
    -0.14
    tero
    -0.14
     Camden
    -0.14
     Wort
    -0.14
    lech
    -0.14
    ยม
    -0.14
    tsy
    -0.13
    tas
    -0.13
    POSITIVE LOGITS
     cons
    1.33
    Cons
    1.27
     Cons
    1.25
    cons
    1.23
    -cons
    1.21
     conserv
    0.96
    _cons
    0.95
     conservation
    0.94
     Conserv
    0.94
     Kons
    0.92
    Activations Density 0.020%

    No Known Activations