© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37547
    Prev
    Next
    INDEX
    Explanations

    winding down, subsiding, slowing

    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
    pai
    -0.10
     masc
    -0.09
     Burton
    -0.09
     ero
    -0.09
     deterior
    -0.09
     deterioration
    -0.09
    ŀæĢ§
    -0.08
     ëĬĺ
    -0.08
    ï½ŀï½ŀ
    -0.08
    Cancelable
    -0.08
    POSITIVE LOGITS
     subs
    0.33
     cal
    0.25
    subs
    0.21
     calm
    0.19
     quiet
    0.18
    Qui
    0.15
     rec
    0.15
     ab
    0.15
     cool
    0.15
     Qui
    0.15
    Activations Density 0.044%

    No Known Activations