Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41449
    Prev
    Next
    INDEX
    Explanations

    definite articles and phrases indicating importance or emphasis

    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
     newcomer
    -0.14
     newest
    -0.14
     newfound
    -0.14
    .
    -0.14
     lately
    -0.14
     new
    -0.13
    #
    -0.13
    Month
    -0.13
     мÑĸÑģÑı
    -0.13
     newly
    -0.12
    POSITIVE LOGITS
    201
    0.71
    200
    0.65
    199
    0.62
    202
    0.56
    198
    0.55
    197
    0.49
    196
    0.43
    195
    0.38
    194
    0.35
    193
    0.34
    Activations Density 0.069%

    No Known Activations