© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 54757
    Prev
    Next
    INDEX
    Explanations

    the word "as" used in various 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
     as
    -0.22
     как
    -0.17
    artner
    -0.16
    eurs
    -0.15
    ieten
    -0.15
     als
    -0.14
    mür
    -0.14
    Ư
    -0.14
    haven
    -0.14
    ovaná
    -0.14
    POSITIVE LOGITS
     possible
    0.33
    possible
    0.27
     Possible
    0.27
     they
    0.26
    sembl
    0.25
     possÃŃvel
    0.25
     posible
    0.25
    Possible
    0.24
    cert
    0.23
     váºŃy
    0.23
    Activations Density 0.066%

    No Known Activations