© 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. 12443
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate claims of credibility and social injustices

    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
    ัà¹Ī
    -0.15
     sodom
    -0.14
     enthusi
    -0.14
     gratuites
    -0.13
     -*-č↵
    -0.13
    interrupt
    -0.13
    /stretch
    -0.13
    rips
    -0.13
     INTERRU
    -0.13
    icc
    -0.13
    POSITIVE LOGITS
     hub
    0.23
     lack
    0.19
     outright
    0.19
     ap
    0.19
     amor
    0.17
    Hub
    0.17
     regression
    0.17
     medi
    0.17
     Hub
    0.17
     vulnerability
    0.17
    Activations Density 0.543%

    No Known Activations