© 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. 61049
    Prev
    Next
    INDEX
    Explanations

    number of decimal digits

    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
     Dur
    -0.11
     prim
    -0.10
     remainder
    -0.09
    krom
    -0.09
     Romeo
    -0.09
     mod
    -0.09
    IEWS
    -0.09
    _numer
    -0.09
     numerical
    -0.09
    é¾Ħ
    -0.09
    POSITIVE LOGITS
     decimal
    0.27
     precision
    0.26
    dec
    0.22
     Decimal
    0.21
    precision
    0.21
    decimal
    0.21
     Precision
    0.21
    Precision
    0.20
     dec
    0.20
     déc
    0.19
    Activations Density 0.058%

    No Known Activations