© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29580
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terminology and the challenges within academic discussions

    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
     “
    -0.15
     thru
    -0.14
    ..
    -0.13
     in
    -0.13
    ,
    -0.13
    .cc
    -0.13
    2
    -0.12
     once
    -0.12
     totally
    -0.12
    ’s
    -0.12
    POSITIVE LOGITS
    .)↵↵↵↵
    0.17
    éf
    0.15
    optgroup
    0.15
    .Selenium
    0.15
    HandlerContext
    0.14
    PointerException
    0.14
     thereof
    0.14
    -urlencoded
    0.14
    ArrayOf
    0.14
    ़à¥į
    0.13
    Activations Density 0.024%

    No Known Activations