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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 29954
    Prev
    Next
    INDEX
    Explanations

    digging dirt and holes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subst
    -0.11
     Vander
    -0.10
     Shed
    -0.10
     Erect
    -0.09
    imir
    -0.09
     Barcl
    -0.09
     Pest
    -0.09
     shedding
    -0.09
    airo
    -0.09
     breadcrumb
    -0.08
    POSITIVE LOGITS
     dig
    0.38
     digging
    0.34
    dig
    0.34
     Dig
    0.33
    Dig
    0.33
     earth
    0.28
     dug
    0.28
     digs
    0.27
     DIG
    0.24
     ÄijÃło
    0.24
    Activations Density 0.078%

    No Known Activations