© 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. 25029
    Prev
    Next
    INDEX
    Explanations

    content related to editorial sections and opinion pieces 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
    owie
    -0.15
    erval
    -0.15
    usercontent
    -0.14
    orpor
    -0.14
    endas
    -0.14
    sic
    -0.14
    åĽ
    -0.13
    apon
    -0.13
    çłĤ
    -0.13
     versa
    -0.13
    POSITIVE LOGITS
     newsletter
    0.18
    âĦ¢
    0.16
     section
    0.16
     CONTRIBUTORS
    0.16
    rief
    0.16
    otch
    0.16
     EXTRA
    0.16
    hek
    0.15
    blick
    0.15
    ì²Ļ
    0.15
    Activations Density 0.202%

    No Known Activations