© 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. 13951
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to official documentation and governance issues

    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
    ses
    -0.16
     Congress
    -0.15
    ilities
    -0.15
    d
    -0.14
    iator
    -0.14
    ilarity
    -0.14
    ropa
    -0.14
     congress
    -0.14
    innamon
    -0.14
     Quar
    -0.14
    POSITIVE LOGITS
    ction
    0.39
    ctions
    0.35
    CT
    0.34
    CTION
    0.34
    ct
    0.34
    екÑĤоÑĢ
    0.32
    екÑĤ
    0.32
    ECT
    0.32
     CT
    0.31
     ct
    0.31
    Activations Density 0.011%

    No Known Activations