© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1395
    Prev
    Next
    INDEX
    Explanations

    cities were overtaken, they were gagged, we will sign

    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
     immediately
    -0.10
    iller
    -0.10
    remain
    -0.09
     sofort
    -0.09
     continued
    -0.09
    amps
    -0.09
     continue
    -0.09
    ãĤ£
    -0.08
     continues
    -0.08
     remain
    -0.08
    POSITIVE LOGITS
     had
    0.14
     داشت
    0.12
     completely
    0.12
    å·²ç»ı
    0.11
     Äijang
    0.11
     entire
    0.11
     estava
    0.10
     estar
    0.10
     was
    0.10
    æŃ£åľ¨
    0.10
    Activations Density 0.042%

    No Known Activations