© 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. 14293
    Prev
    Next
    INDEX
    Explanations

    assuming or already

    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
     inception
    -0.09
     seems
    -0.09
    keterangan
    -0.09
     Cham
    -0.08
     seem
    -0.08
    سÙĪ
    -0.08
    arend
    -0.08
    eli
    -0.08
     coward
    -0.08
     Leon
    -0.08
    POSITIVE LOGITS
     already
    0.20
     Already
    0.15
    Already
    0.15
    already
    0.14
    å·²ç»ı
    0.13
     zaten
    0.12
     bereits
    0.12
     somewhere
    0.11
     Ñĥже
    0.11
     już
    0.11
    Activations Density 0.028%

    No Known Activations