© 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. 43821
    Prev
    Next
    INDEX
    Explanations

    importing financial analysis libraries

    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
    éra
    -0.09
    æĶ¶åħ¥
    -0.09
     Wass
    -0.09
    undler
    -0.09
    edian
    -0.09
    ERM
    -0.09
     ETA
    -0.09
    enia
    -0.08
    æĪ
    -0.08
    IGO
    -0.08
    POSITIVE LOGITS
     signals
    0.15
     signal
    0.13
     candle
    0.13
    ä»ĵ
    0.13
     rolling
    0.13
     lag
    0.13
     buy
    0.13
     daily
    0.12
     Buy
    0.12
     candles
    0.12
    Activations Density 0.081%

    No Known Activations