© 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. 8477
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "result"

    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
    ighton
    -0.16
    alus
    -0.15
    tran
    -0.15
    igel
    -0.14
    Injected
    -0.14
    alls
    -0.13
     Goodman
    -0.13
    ãĤĩãģĨ
    -0.13
    emoc
    -0.13
    esta
    -0.13
    POSITIVE LOGITS
     in
    0.31
    antly
    0.21
    à¹ĥà¸Ļ
    0.20
    CppClass
    0.18
    CppType
    0.18
    à¹ĥà¸Ļส
    0.18
     în
    0.17
    åľ¨
    0.17
    à¹ĥà¸Ļร
    0.17
    ados
    0.17
    Activations Density 0.021%

    No Known Activations