© 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. 41194
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" 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
     supposedly
    -0.19
     Probably
    -0.17
     probably
    -0.17
     reportedly
    -0.16
     presumably
    -0.16
    croft
    -0.16
    Probably
    -0.15
    esin
    -0.15
    probably
    -0.15
     reputed
    -0.15
    POSITIVE LOGITS
     quite
    0.21
     somewhat
    0.18
     rather
    0.17
    lopen
    0.16
     endless
    0.16
     khá
    0.15
     bastante
    0.15
    fall
    0.15
     fairly
    0.15
     lately
    0.15
    Activations Density 0.044%

    No Known Activations