© 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. 9476
    Prev
    Next
    INDEX
    Explanations

    device may requirebot could requiredetection can be challengingStates can beUI may not

    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
     Fraser
    -0.09
     Anton
    -0.09
    untu
    -0.09
     tempt
    -0.09
    anton
    -0.08
    iro
    -0.08
     stren
    -0.08
    reh
    -0.08
     simply
    -0.08
     Faster
    -0.08
    POSITIVE LOGITS
     challenging
    0.26
     requires
    0.24
     require
    0.24
     challenge
    0.23
     challenges
    0.20
     difficult
    0.19
     requ
    0.18
    requires
    0.18
     challenged
    0.18
     Challenge
    0.17
    Activations Density 0.181%

    No Known Activations