© 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. 15387
    Prev
    Next
    INDEX
    Explanations

    phrases related to the decline of liberal arts education and its perceived disadvantages

    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
     leisure
    -0.15
    «a
    -0.14
    Slow
    -0.14
     qual
    -0.14
     philosoph
    -0.14
    HeaderCode
    -0.14
    ëıħ
    -0.13
    .openConnection
    -0.13
    entarios
    -0.13
    .SizeType
    -0.13
    POSITIVE LOGITS
     practical
    0.79
     Practical
    0.70
     pragmatic
    0.53
     prag
    0.47
     prakt
    0.42
     concrete
    0.41
    actical
    0.34
     Concrete
    0.32
    Concrete
    0.32
     functional
    0.31
    Activations Density 0.024%

    No Known Activations