© 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. 3259
    Prev
    Next
    INDEX
    Explanations

    list and therefore

    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
    ï¼ĮåĽłä¸º
    -0.13
    onen
    -0.11
    ï¼Įä¸įè¿ĩ
    -0.10
     especially
    -0.10
     ìŀĪëĬĶëį°
    -0.09
     اÙĦبتÙĩ
    -0.09
     iÅŁte
    -0.09
     olsun
    -0.09
    ãģłãģ£ãģ¦
    -0.09
     Sof
    -0.09
    POSITIVE LOGITS
    ï¼ĮæīĢ以
    0.37
    æīĢ以
    0.36
     takže
    0.33
     nên
    0.33
     therefore
    0.33
     Therefore
    0.32
    Therefore
    0.31
     поÑįÑĤомÑĥ
    0.30
    ï¼ĮåĽłæѤ
    0.28
     wiÄĻc
    0.26
    Activations Density 0.278%

    No Known Activations