© 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. 43018
    Prev
    Next
    INDEX
    Explanations

    phrases related to support and growth within communities or organizations

    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
     jadx
    -0.15
    á»ij
    -0.15
    ạn
    -0.14
     sporting
    -0.14
     Sporting
    -0.14
     athletic
    -0.14
    DDevice
    -0.14
    åŃĿ
    -0.13
     Sok
    -0.13
    rica
    -0.13
    POSITIVE LOGITS
    iah
    0.14
     excellence
    0.14
    herent
    0.14
     lovers
    0.13
    ิà¸Ĭ
    0.13
    endant
    0.13
    idget
    0.13
    zure
    0.13
     lover
    0.13
     hostage
    0.13
    Activations Density 0.109%

    No Known Activations