© 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. 43400
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions

    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
    yor
    -0.16
    angl
    -0.16
    à¥Ĥप
    -0.14
     realpath
    -0.14
    Å¡ak
    -0.13
    allas
    -0.13
    ÏģοÏĤ
    -0.13
    ognito
    -0.13
    iyel
    -0.13
    à¹Ģà¸Ķà¸Ńร
    -0.13
    POSITIVE LOGITS
     about
    0.61
     around
    0.60
     approximately
    0.52
    around
    0.50
    about
    0.49
    About
    0.46
     About
    0.46
     Around
    0.45
    Around
    0.44
    ç´Ħ
    0.43
    Activations Density 0.134%

    No Known Activations