© 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. 37497
    Prev
    Next
    INDEX
    Explanations

    economy and financial markets

    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
    ibel
    -0.10
    icl
    -0.10
     pard
    -0.09
     nearest
    -0.09
     dossier
    -0.09
    üh
    -0.09
     sl
    -0.09
     turnover
    -0.08
    ThreadId
    -0.08
    bine
    -0.08
    POSITIVE LOGITS
     economy
    0.19
     markets
    0.15
     Economy
    0.13
    orr
    0.12
     company
    0.12
    conomy
    0.12
    Street
    0.12
    erra
    0.11
     Fed
    0.11
    chor
    0.11
    Activations Density 0.076%

    No Known Activations