© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44551
    Prev
    Next
    INDEX
    Explanations

    Leading businesses consult large

    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
     mogul
    -0.09
    nder
    -0.09
     Entre
    -0.09
     jobs
    -0.09
     businessman
    -0.09
     CSR
    -0.09
     fore
    -0.09
     Businesses
    -0.09
     pivot
    -0.09
    Entre
    -0.09
    POSITIVE LOGITS
     Fortune
    0.23
     fortune
    0.19
    fortune
    0.16
     medium
    0.13
     large
    0.12
     repl
    0.11
     vertical
    0.11
     regulated
    0.11
     mature
    0.11
     sectors
    0.11
    Activations Density 0.152%

    No Known Activations