© 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. 63976
    Prev
    Next
    INDEX
    Explanations

    efficient user experience

    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
     hors
    -0.11
    unga
    -0.09
    atura
    -0.09
     Succ
    -0.09
    ãĥ¼ãĥį
    -0.09
    abo
    -0.09
     frivol
    -0.08
    uli
    -0.08
     expend
    -0.08
     incur
    -0.08
    POSITIVE LOGITS
     experience
    0.50
    experience
    0.38
     Experience
    0.36
     experiencia
    0.34
    Experience
    0.33
     expérience
    0.31
     experiences
    0.31
     experi
    0.28
    _experience
    0.27
    perience
    0.26
    Activations Density 0.094%

    No Known Activations