© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 30552
    Prev
    Next
    INDEX
    Explanations

    mentions of positions related to faculty and changes in the academic workforce

    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
     resemble
    -0.18
     resembles
    -0.17
    ucceeded
    -0.16
     zvol
    -0.16
    apat
    -0.16
    ancellable
    -0.16
    å¤ļãģĦ
    -0.16
    indir
    -0.16
    ipay
    -0.16
     gotten
    -0.15
    POSITIVE LOGITS
     was
    0.23
    Ñĭвал
    0.20
    ноÑģи
    0.20
     operated
    0.20
     controlled
    0.20
    ãģĹãģ¦ãģĦãģŁ
    0.20
     knew
    0.20
    ãģ£ãģ¦ãģĦãģŁ
    0.19
     existed
    0.19
    used
    0.19
    Activations Density 0.167%

    No Known Activations