© 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 EvalsExportsAPI 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. 14346
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     occasionally
    -0.15
     Occasionally
    -0.13
    agua
    -0.12
    ijken
    -0.12
    ÃŃme
    -0.12
    âĢİ
    -0.12
     cancelButtonTitle
    -0.12
     Ú©ÙĪÚĨ
    -0.11
    INLINE
    -0.11
    zan
    -0.11
    POSITIVE LOGITS
     very
    0.28
     greatly
    0.25
     lots
    0.25
     many
    0.24
     sehr
    0.22
    lots
    0.21
     really
    0.21
    å¾Īå¤ļ
    0.21
     mainly
    0.21
     mostly
    0.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.