© 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. 30862
    Prev
    Next
    INDEX
    Explanations

    defining therapies and companies

    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
     może
    -0.12
    might
    -0.12
     могли
    -0.12
     possono
    -0.11
     могÑĥÑĤ
    -0.11
    åı¯èĥ½
    -0.11
    à¸Ńาà¸Ī
    -0.11
     могла
    -0.11
     might
    -0.11
     poate
    -0.11
    POSITIVE LOGITS
     is
    0.20
     adalah
    0.19
     är
    0.19
     είναι
    0.15
     lÃł
    0.15
     are
    0.15
    æĺ¯ä¸Ģ
    0.15
    æĺ¯ä¸Ģ个
    0.15
     æĺ¯
    0.15
    æĺ¯
    0.13
    Activations Density 0.122%

    No Known Activations