© 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. 54902
    Prev
    Next
    INDEX
    Explanations

    practical application and learning

    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
     Castro
    -0.10
     Hog
    -0.09
    tility
    -0.08
     ucwords
    -0.08
    ëį°ìĿ´íĬ¸
    -0.08
     Haus
    -0.08
    Routine
    -0.08
    ÑĤап
    -0.08
    ucas
    -0.08
    ibi
    -0.08
    POSITIVE LOGITS
     hands
    0.36
     Hands
    0.29
     practical
    0.29
    hands
    0.27
     exper
    0.25
    Hands
    0.25
     Practical
    0.23
     experience
    0.19
     prakt
    0.18
     practice
    0.18
    Activations Density 0.113%

    No Known Activations