© 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. 58256
    Prev
    Next
    INDEX
    Explanations

    a/an followed by description

    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
    инов
    -0.09
    913
    -0.09
    ï½Ģ
    -0.08
    çak
    -0.08
     ÙħÙĪاط
    -0.08
    æ½ľ
    -0.08
    PRINTF
    -0.08
    主人
    -0.08
    GGLE
    -0.08
    .Factory
    -0.08
    POSITIVE LOGITS
     sight
    0.24
     bit
    0.17
    gh
    0.14
     Sight
    0.13
     ver
    0.13
     fixture
    0.13
     bundle
    0.12
    flutter
    0.12
     changed
    0.12
     ways
    0.12
    Activations Density 0.049%

    No Known Activations