© 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. 56015
    Prev
    Next
    INDEX
    Explanations

    such as, or

    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
     such
    -0.17
    such
    -0.15
     like
    -0.12
     ترÛĮÙĨ
    -0.10
     zoals
    -0.10
     SUCH
    -0.10
     seperti
    -0.10
    898
    -0.10
    ãģ¨ãģĦãģĨ
    -0.10
     Bout
    -0.09
    POSITIVE LOGITS
     ones
    0.16
     etc
    0.15
    etc
    0.13
     which
    0.11
     whose
    0.10
    477
    0.09
     Julien
    0.09
     коÑĤоÑĢÑĭе
    0.09
    ulp
    0.09
    whose
    0.09
    Activations Density 0.145%

    No Known Activations