© 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. 33522
    Prev
    Next
    INDEX
    Explanations

    references to dates and events in a political context

    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
    ĵĺ
    -0.15
    abbo
    -0.14
    ाà¤ĩन
    -0.14
     Ariel
    -0.13
     Aurora
    -0.13
     Abyss
    -0.13
    Ĥ¹
    -0.13
    advisor
    -0.13
    oleon
    -0.12
     Ott
    -0.12
    POSITIVE LOGITS
     ãĤ¨
    0.28
    ãĤ¨
    0.28
     Ñį
    0.26
     е
    0.26
    à§ĩ
    0.25
     ÐŃ
    0.24
    _E
    0.24
     ìĹIJ
    0.23
    _e
    0.22
    ÄĻ
    0.22
    Activations Density 0.136%

    No Known Activations