© 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. 44158
    Prev
    Next
    INDEX
    Explanations

    terms related to liver regeneration and related biological pathways

    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
    olini
    -0.18
     Ros
    -0.15
     racket
    -0.15
    phis
    -0.14
    Formats
    -0.14
     Formats
    -0.14
     pů
    -0.14
     Metro
    -0.14
    ozor
    -0.13
     stap
    -0.13
    POSITIVE LOGITS
     genes
    0.74
     gene
    0.59
    genes
    0.55
    _genes
    0.50
     Gene
    0.47
    gene
    0.46
    Gene
    0.43
    _gene
    0.40
     proteins
    0.35
     Geneva
    0.31
    Activations Density 0.036%

    No Known Activations