© 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. 8844
    Prev
    Next
    INDEX
    Explanations

    instances of the word "evidenced."

    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
     as
    -0.20
    ä½ľä¸º
    -0.17
     als
    -0.17
     sebagai
    -0.16
    reau
    -0.16
    аÑĢаÑĤ
    -0.16
     jako
    -0.15
    eren
    -0.15
    ht
    -0.14
     accompanied
    -0.14
    POSITIVE LOGITS
     by
    0.34
     تÙĪØ³Ø·
    0.25
     oleh
    0.23
    by
    0.21
     напÑĢимеÑĢ
    0.19
     napÅĻÃŃklad
    0.18
     ÙħØ«ÙĦا
    0.18
    _by
    0.17
     bợi
    0.17
    à¹Ĥà¸Ķย
    0.16
    Activations Density 0.033%

    No Known Activations