© 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. 24316
    Prev
    Next
    INDEX
    Explanations

    informative and age-appropriate

    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
    çļĦ人
    -0.11
     teenage
    -0.11
     Ladies
    -0.10
     toddler
    -0.10
     infancy
    -0.09
     nursery
    -0.09
     uplifting
    -0.09
     eros
    -0.09
     community
    -0.09
     Couples
    -0.09
    POSITIVE LOGITS
     fun
    0.18
     age
    0.18
     teaching
    0.17
     kids
    0.16
     Fun
    0.16
     teach
    0.15
     children
    0.14
     learning
    0.14
     appropri
    0.14
    åŃ©åŃIJ
    0.14
    Activations Density 0.141%

    No Known Activations