© 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. 44720
    Prev
    Next
    INDEX
    Explanations

    concepts related to assessment and evaluation

    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
    'gc
    -0.18
     Woodward
    -0.14
    istar
    -0.14
    OUNCE
    -0.14
    adden
    -0.14
    udden
    -0.14
    .until
    -0.14
    dre
    -0.14
    pes
    -0.13
    åı¤
    -0.13
    POSITIVE LOGITS
     successes
    0.33
     lessons
    0.32
    lessons
    0.29
     Lessons
    0.29
     highlights
    0.24
     triumph
    0.23
     highs
    0.22
     progress
    0.22
     pros
    0.21
    æĮ¯ãĤĬ
    0.21
    Activations Density 0.017%

    No Known Activations