© 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. 43677
    Prev
    Next
    INDEX
    Explanations

    prices, demand, pressure

    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
     productivity
    -0.09
     Sour
    -0.09
     dimin
    -0.09
     overnight
    -0.09
    TEL
    -0.09
    æ¯Ķ
    -0.09
     Mobility
    -0.08
    ponce
    -0.08
    rig
    -0.08
     succ
    -0.08
    POSITIVE LOGITS
     overall
    0.21
     demand
    0.18
     pressure
    0.16
    overall
    0.15
     Overall
    0.15
     demande
    0.14
     Demand
    0.14
     Pressure
    0.14
     demands
    0.13
    Overall
    0.13
    Activations Density 0.079%

    No Known Activations