© 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. 21377
    Prev
    Next
    INDEX
    Explanations

    references to data specifications and components in technical documents

    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
    orton
    -0.15
    esson
    -0.14
    ornment
    -0.14
    idi
    -0.13
    lander
    -0.13
    athi
    -0.13
    pte
    -0.13
    FileManager
    -0.13
    اÙĤع
    -0.13
    azzo
    -0.13
    POSITIVE LOGITS
     specifications
    0.43
     specs
    0.38
     Specifications
    0.36
     specification
    0.35
     features
    0.32
     Features
    0.30
     price
    0.30
     pricing
    0.30
     Specification
    0.30
     spec
    0.29
    Activations Density 0.057%

    No Known Activations