© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 44920
    Prev
    Next
    INDEX
    Explanations

    content related to pricing and costs associated with services

    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
    ãĥ³ãĥĸ
    -0.17
    eman
    -0.14
    -urlencoded
    -0.13
    .getCurrent
    -0.12
    È
    -0.12
     doma
    -0.12
    minster
    -0.12
    OrCreate
    -0.12
    NEXT
    -0.12
    eron
    -0.12
    POSITIVE LOGITS
     above
    1.43
    above
    1.18
     Above
    1.11
    Above
    1.07
     ABOVE
    1.01
    _above
    0.83
    以ä¸Ĭ
    0.79
     вÑĭÑĪе
    0.78
    bove
    0.74
     aforementioned
    0.73
    Activations Density 0.056%

    No Known Activations