© 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. 12512
    Prev
    Next
    INDEX
    Explanations

    references to evaluations and measurements

    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
     Third
    -0.17
     Second
    -0.16
    .opendaylight
    -0.15
     Fifth
    -0.15
    mailto
    -0.15
    ahn
    -0.14
    yclopedia
    -0.14
     Fourth
    -0.14
     Sixth
    -0.14
     Seventh
    -0.14
    POSITIVE LOGITS
     first
    1.13
    first
    0.98
     FIRST
    0.71
     primero
    0.70
     primeiro
    0.68
    .first
    0.66
    -first
    0.65
    	first
    0.64
     먼ìłĢ
    0.63
     eerste
    0.63
    Activations Density 0.043%

    No Known Activations