© 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. 25799
    Prev
    Next
    INDEX
    Explanations

    transitional phrases or conjunctions that connect ideas in a narrative

    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
    uste
    -0.16
    erdale
    -0.14
    antha
    -0.14
     ÑįÑĤомÑĥ
    -0.14
    ModelProperty
    -0.14
    angu
    -0.14
    hlen
    -0.14
    hazi
    -0.14
    ëģĶ
    -0.13
    astle
    -0.13
    POSITIVE LOGITS
     besides
    1.00
     Besides
    0.87
    Besides
    0.82
    bes
    0.74
     Plus
    0.61
     plus
    0.60
    Plus
    0.57
     además
    0.55
    plus
    0.54
     além
    0.50
    Activations Density 0.043%

    No Known Activations