© 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. 14735
    Prev
    Next
    INDEX
    Explanations

    mentions of public figures or entities, particularly related to political discourse

    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
    ằm
    -0.17
    ิà¸Ļà¸Ĺ
    -0.16
    SKU
    -0.15
    öm
    -0.15
    .rar
    -0.15
     Aires
    -0.14
    íħľ
    -0.14
     addCriterion
    -0.14
    rowable
    -0.14
    .usage
    -0.14
    POSITIVE LOGITS
     tweet
    0.29
     tweets
    0.27
     @
    0.27
     twe
    0.25
     Tweets
    0.25
     tweeted
    0.24
    pic
    0.24
     pic
    0.23
     RT
    0.23
     Twitter
    0.23
    Activations Density 0.090%

    No Known Activations