© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 42301
    Prev
    Next
    INDEX
    Explanations

    geometrical shapes and their representations

    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
    .UnitTesting
    -0.21
     Annunci
    -0.16
    manship
    -0.15
    erable
    -0.15
    ORIZONTAL
    -0.15
    elijk
    -0.15
    nbsp
    -0.14
    PHY
    -0.14
    ility
    -0.14
    eration
    -0.14
    POSITIVE LOGITS
    icals
    0.22
    -eyed
    0.22
    -shaped
    0.21
    uate
    0.19
    ically
    0.18
    ill
    0.18
    ind
    0.17
    -headed
    0.16
    ical
    0.16
    wright
    0.16
    Activations Density 0.003%

    No Known Activations