© 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. 8566
    Prev
    Next
    INDEX
    Explanations

    mentions of languages and their associated contexts

    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
    legg
    -0.14
    itionally
    -0.14
    isphere
    -0.14
    annonce
    -0.13
    ssf
    -0.13
     Loud
    -0.13
     norske
    -0.13
    claimer
    -0.13
     ç§
    -0.13
    itial
    -0.13
    POSITIVE LOGITS
    -speaking
    0.31
    -language
    0.28
     language
    0.28
    language
    0.22
     spoken
    0.21
    -medium
    0.21
    -spe
    0.21
     Language
    0.20
     ÑıзÑĭ
    0.19
    lish
    0.19
    Activations Density 0.053%

    No Known Activations