© 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. 12903
    Prev
    Next
    INDEX
    Explanations

    positive adjectives used to describe experiences or characteristics

    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
    ï¼Į以åıĬ
    -0.18
     whose
    -0.17
     rather
    -0.17
     (“
    -0.16
     when
    -0.16
     whenever
    -0.15
     that
    -0.15
    ç«
    -0.15
    æ°ĹãģĮ
    -0.14
     simply
    -0.13
    POSITIVE LOGITS
    _like
    0.18
    uin
    0.17
    ä½Ĩ
    0.17
     like
    0.17
     pero
    0.17
     etc
    0.17
     но
    0.16
    stanov
    0.16
     lots
    0.16
     but
    0.15
    Activations Density 0.022%

    No Known Activations