© 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. 32219
    Prev
    Next
    INDEX
    Explanations

    underground cell dug into ground

    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
    rones
    -0.10
     rooft
    -0.09
     paras
    -0.09
     Weather
    -0.09
    tej
    -0.09
    icopt
    -0.09
     sabot
    -0.09
     balcon
    -0.08
    isempty
    -0.08
     dumpsters
    -0.08
    POSITIVE LOGITS
     underground
    0.43
    åľ°ä¸ĭ
    0.38
     Underground
    0.35
     basement
    0.28
     cellar
    0.21
    åľ¨åľ°
    0.21
    à¹ĥà¸ķ
    0.20
     Basement
    0.20
     below
    0.19
     Below
    0.18
    Activations Density 0.067%

    No Known Activations