© 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 EvalsExportsinterp-engineNEWAPI 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. 12560
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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
    åīĩ
    -0.14
    imento
    -0.13
    oro
    -0.13
    bulk
    -0.13
    oom
    -0.13
    à¸ļาล
    -0.13
    Bulk
    -0.13
    .forChild
    -0.13
     Bulk
    -0.13
    Ñĥди
    -0.13
    POSITIVE LOGITS
    Anyway
    0.88
     anyway
    0.86
     Anyway
    0.85
     anyways
    0.66
     anyhow
    0.53
     toch
    0.30
     nonetheless
    0.28
    ANY
    0.28
     nevertheless
    0.26
    any
    0.26
    Activations Density 0.180%

    No Known Activations