© 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. 13791
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "that being said."

    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
     to
    -0.14
     Pont
    -0.14
    .surname
    -0.14
    -unused
    -0.14
     prompt
    -0.13
    -expand
    -0.13
    rror
    -0.13
    Workbook
    -0.13
     Stephens
    -0.13
    _HS
    -0.13
    POSITIVE LOGITS
     said
    0.19
    bek
    0.16
    еÑĢÑĮ
    0.16
    бÑĥдÑĮ
    0.15
    WithPath
    0.14
    elon
    0.14
    typeid
    0.14
    éra
    0.14
    .om
    0.13
    ä¹ĭä¸Ģ
    0.13
    Activations Density 0.018%

    No Known Activations