© 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. 9161
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" 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
     hereby
    -0.18
     now
    -0.17
    now
    -0.16
    ();)
    -0.16
    still
    -0.16
     NOT
    -0.15
    NOW
    -0.15
     STILL
    -0.15
    uku
    -0.15
     ancora
    -0.14
    POSITIVE LOGITS
     previously
    0.32
     earlier
    0.27
     previous
    0.25
     Previously
    0.21
     Previous
    0.20
    Previously
    0.18
    (previous
    0.18
     preceded
    0.18
    Earlier
    0.18
    Previous
    0.18
    Activations Density 0.072%

    No Known Activations