© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 30643
    Prev
    Next
    INDEX
    Explanations

    terms related to datasets and their structures in contexts involving cultural concepts

    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
     fare
    -0.15
     sep
    -0.13
     usual
    -0.13
    ÑĨенÑĤÑĢа
    -0.13
     Gay
    -0.13
    ardu
    -0.12
     omn
    -0.12
     mening
    -0.12
    remen
    -0.12
     ragaz
    -0.12
    POSITIVE LOGITS
     èĩªåĬ¨çĶŁæĪIJ
    0.15
     generated
    0.15
     hereby
    0.15
     output
    0.14
    çĶŁæĪIJ
    0.14
     ÑģооÑĤ
    0.14
     finally
    0.14
    createForm
    0.13
     generate
    0.13
    GeneratedValue
    0.13
    Activations Density 0.088%

    No Known Activations