© 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. 43593
    Prev
    Next
    INDEX
    Explanations

    references to syndicated columns and advice in media

    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
    elsen
    -0.15
    åħ¸
    -0.14
    .jackson
    -0.14
    study
    -0.13
    areth
    -0.13
    IFORM
    -0.13
    _ACCEPT
    -0.13
    ersion
    -0.13
     study
    -0.13
    ftime
    -0.13
    POSITIVE LOGITS
     column
    0.75
     columns
    0.69
    column
    0.61
     Column
    0.61
     Columns
    0.55
    -column
    0.55
    Column
    0.54
    columns
    0.54
     columna
    0.53
     columnist
    0.49
    Activations Density 0.035%

    No Known Activations