© 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. 22286
    Prev
    Next
    INDEX
    Explanations

    references to various media outlets and their operations

    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
    itters
    -0.15
    TEGER
    -0.15
     Advertisement
    -0.15
    acomment
    -0.14
    ัà¸ķà¸ĸ
    -0.13
    Advertisement
    -0.13
    shal
    -0.13
     pha
    -0.13
     camer
    -0.13
    ÑģÑĤоÑĢиÑı
    -0.12
    POSITIVE LOGITS
     publications
    0.37
     magazines
    0.37
     publication
    0.36
     magazine
    0.33
    mag
    0.29
     newspapers
    0.28
    publication
    0.27
     outlets
    0.27
     outlet
    0.25
     Magazine
    0.25
    Activations Density 0.093%

    No Known Activations