© 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. 23710
    Prev
    Next
    INDEX
    Explanations

    trade-off between options

    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
    MING
    -0.09
    terra
    -0.09
    票
    -0.09
    zek
    -0.09
    MLS
    -0.09
     peg
    -0.09
    .hd
    -0.08
     Andersen
    -0.08
    wan
    -0.08
     scr
    -0.08
    POSITIVE LOGITS
     trade
    0.57
    trade
    0.45
     Trade
    0.44
    Trade
    0.39
    -trade
    0.33
    _trade
    0.32
     compromise
    0.30
     TRADE
    0.29
     traded
    0.29
     trades
    0.29
    Activations Density 0.077%

    No Known Activations