© 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. 13560
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and associated sentence structures

    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
    AndView
    -0.13
    ëħĦìĹIJëĬĶ
    -0.13
    .xmlbeans
    -0.12
    iaux
    -0.12
     Lyn
    -0.12
    ãĥ³ãĥķ
    -0.12
    stered
    -0.12
    æ
    -0.11
    Yaw
    -0.11
    aimassage
    -0.11
    POSITIVE LOGITS
     âĢ¦.
    0.14
    exampleInput
    0.14
     nederland
    0.14
     âĢ¦↵
    0.14
     ...)
    0.13
    лаÑĢа
    0.13
     Âł
    0.13
    amment
    0.13
     âĢ¦
    0.13
    )--
    0.12
    Activations Density 0.024%

    No Known Activations