© 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. 57777
    Prev
    Next
    INDEX
    Explanations

    functional programming languages

    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
    iras
    -0.10
     UA
    -0.10
     McCoy
    -0.10
     iter
    -0.09
     turkey
    -0.09
     Gardner
    -0.09
     Federation
    -0.09
    /lab
    -0.09
     Ionic
    -0.09
     Turkey
    -0.08
    POSITIVE LOGITS
     functional
    0.29
     Functional
    0.27
    Functional
    0.25
    functional
    0.23
    -functional
    0.21
     Clo
    0.18
     FP
    0.18
    FP
    0.16
     Curry
    0.16
     Haskell
    0.16
    Activations Density 0.070%

    No Known Activations