© 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. 28249
    Prev
    Next
    INDEX
    Explanations

    criticism of television programming and its lack of intellectual depth

    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
    ©
    -0.14
    Visible
    -0.14
     Äijá»Ļng
    -0.14
     '&#
    -0.14
     bindActionCreators
    -0.14
    ynam
    -0.14
    osome
    -0.13
     Mutable
    -0.13
    ä¹ł
    -0.13
    ↵↵
    -0.13
    POSITIVE LOGITS
     sophisticated
    0.39
     sophistication
    0.38
     sophistic
    0.30
     refined
    0.28
     intellectuals
    0.28
     cultured
    0.28
     intellectual
    0.28
     serious
    0.27
     Intellectual
    0.26
     classy
    0.26
    Activations Density 0.025%

    No Known Activations