© 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. 53787
    Prev
    Next
    INDEX
    Explanations

    conclusion or punctuation

    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
    ï¼Į以åıĬ
    -0.16
    ï¼ĮåIJĮæŶ
    -0.14
    以åıĬ
    -0.11
     oraz
    -0.11
     sowie
    -0.11
     ìŀĪëĬĶëį°
    -0.11
    ãģĵãģĿ
    -0.11
     serta
    -0.10
     ÙĪØ°ÙĦÙĥ
    -0.10
    íķĺëĬĶëį°
    -0.10
    POSITIVE LOGITS
     nên
    0.16
     seh
    0.15
     Therefore
    0.14
     therefore
    0.14
     takže
    0.14
    æīĢ以
    0.13
    Therefore
    0.12
     поÑįÑĤомÑĥ
    0.12
    ë¯Ģë¡ľ
    0.12
     so
    0.11
    Activations Density 0.244%

    No Known Activations