© 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. 22878
    Prev
    Next
    INDEX
    Explanations

    simple and contented life

    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
     badly
    -0.10
     worldly
    -0.10
     secular
    -0.09
     Smooth
    -0.09
     op
    -0.09
     zim
    -0.08
     professionalism
    -0.08
     neutr
    -0.08
     sheer
    -0.08
     adult
    -0.08
    POSITIVE LOGITS
     simplicity
    0.22
     simple
    0.21
     rural
    0.21
     SIMPLE
    0.20
     simpler
    0.20
     Simple
    0.19
     authenticity
    0.18
     Rural
    0.18
    Simple
    0.18
     slower
    0.18
    Activations Density 0.137%

    No Known Activations