© 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. 20601
    Prev
    Next
    INDEX
    Explanations

    components and relationships

    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
    çļĦä¸Ģ个
    -0.12
    ä¸Ģ个
    -0.11
     an
    -0.11
     another
    -0.11
     eine
    -0.10
     een
    -0.10
    \tan
    -0.09
    åı¦
    -0.09
     beiden
    -0.09
     einen
    -0.09
    POSITIVE LOGITS
     the
    0.14
     los
    0.10
     their
    0.10
     those
    0.10
     những
    0.10
     các
    0.09
     individual
    0.09
     las
    0.09
     dei
    0.09
     mere
    0.08
    Activations Density 0.234%

    No Known Activations