© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44497
    Prev
    Next
    INDEX
    Explanations

    genius, brilliant, intelligent

    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
     reg
    -0.10
     Journalism
    -0.10
     imagin
    -0.09
    RuntimeObject
    -0.09
    bew
    -0.08
     soph
    -0.08
     inst
    -0.08
    slu
    -0.08
     Vall
    -0.08
     Lowest
    -0.08
    POSITIVE LOGITS
     genius
    0.42
     Genius
    0.36
     prod
    0.34
     gen
    0.33
    gen
    0.28
     brilliant
    0.27
     GEN
    0.26
     brill
    0.26
     gén
    0.26
     brilliance
    0.26
    Activations Density 0.199%

    No Known Activations