© 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. 14878
    Prev
    Next
    INDEX
    Explanations

    machine learning regression

    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
    ij
    -0.11
    iale
    -0.10
     :ï¼¼
    -0.09
    ogan
    -0.09
    teenth
    -0.09
     Regulations
    -0.09
    icator
    -0.08
    à¸Ľà¸£à¸°à¸¡à¸²à¸ĵ
    -0.08
    ings
    -0.08
    ahan
    -0.08
    POSITIVE LOGITS
    ions
    0.18
    ional
    0.17
     spl
    0.13
    (reg
    0.12
     model
    0.12
     analysis
    0.12
     reg
    0.10
    ist
    0.10
    istory
    0.10
     Spl
    0.10
    Activations Density 0.019%

    No Known Activations