© 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. 44085
    Prev
    Next
    INDEX
    Explanations

    discussions about nuanced approaches to social or political issues

    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
     rud
    -0.16
     fixed
    -0.14
     Crossing
    -0.14
    åĽº
    -0.14
     sped
    -0.14
     Retro
    -0.13
     poorer
    -0.13
    -invalid
    -0.13
    çİĩ
    -0.13
     comparable
    -0.13
    POSITIVE LOGITS
     nuanced
    0.28
     nu
    0.27
     flexibility
    0.27
     flexible
    0.26
     moderation
    0.26
     cautious
    0.25
     gent
    0.23
     moderate
    0.23
     ambiguity
    0.23
     tháºŃn
    0.22
    Activations Density 0.111%

    No Known Activations