© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28735
    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
     Interpret
    -0.15
    ÙĪÙĨا
    -0.14
    assis
    -0.14
    FileVersion
    -0.14
    oup
    -0.14
     treatment
    -0.14
     Trou
    -0.14
    ync
    -0.14
    nen
    -0.14
    ões
    -0.13
    POSITIVE LOGITS
     convey
    0.24
     emphasis
    0.22
     describe
    0.22
    mean
    0.19
     express
    0.19
     refer
    0.18
     mean
    0.18
     descri
    0.18
     indicate
    0.18
    describe
    0.18
    Activations Density 0.083%

    No Known Activations