© 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 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. 43322
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating additional information or emphasis

    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
    -д
    -0.28
     ड
    -0.27
    -d
    -0.27
     à¸Ķ
    -0.25
    ÂłÐ´
    -0.25
     ÐĶ
    -0.25
     Democrats
    -0.25
     द
    -0.24
    Âłd
    -0.24
     dioxide
    -0.23
    POSITIVE LOGITS
    dup
    0.18
    die
    0.18
    dig
    0.17
    dr
    0.16
     applicationWill
    0.15
    DEN
    0.15
    dep
    0.15
    dash
    0.15
    deg
    0.15
    dim
    0.15
    Activations Density 0.005%

    No Known Activations