© 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. 23051
    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
    intree
    -0.18
    its
    -0.17
    amu
    -0.15
    'gc
    -0.14
    linger
    -0.14
    ROP
    -0.14
    unk
    -0.13
    ystone
    -0.13
    iko
    -0.13
    first
    -0.13
    POSITIVE LOGITS
    erosis
    0.17
    avax
    0.16
    erli
    0.15
    onis
    0.14
    dpi
    0.14
    оÑĢаз
    0.14
    EFA
    0.14
    anco
    0.14
     sincer
    0.14
    bane
    0.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.