© 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. 18058
    Prev
    Next
    INDEX
    Explanations

    identify areas or issues

    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
    EGA
    -0.09
    unda
    -0.09
     Shannon
    -0.09
     rue
    -0.08
    908
    -0.08
    amage
    -0.08
     Rue
    -0.08
    ATES
    -0.08
     inconsistencies
    -0.08
    ãĢĢ ãĢĢ ãĢĢ ãĢĢ ãĢĢ
    -0.08
    POSITIVE LOGITS
     areas
    0.37
     Areas
    0.28
    areas
    0.26
    Areas
    0.25
    _areas
    0.22
     weak
    0.22
     áreas
    0.21
     area
    0.20
     where
    0.18
     ways
    0.18
    Activations Density 0.035%

    No Known Activations