© 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. 51996
    Prev
    Next
    INDEX
    Explanations

    subject followed by possibility

    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
    'gc
    -0.10
     Willie
    -0.09
     telah
    -0.09
    ázev
    -0.09
     Äijang
    -0.09
     çĿ
    -0.09
     hasNext
    -0.09
    нили
    -0.09
     Willow
    -0.09
    abilece
    -0.09
    POSITIVE LOGITS
     will
    0.34
     sẽ
    0.30
    å°±ä¼ļ
    0.27
     akan
    0.26
    will
    0.25
     likely
    0.24
     becomes
    0.24
    ä¼ļ
    0.24
     бÑĥдеÑĤ
    0.23
    æľĥ
    0.23
    Activations Density 0.222%

    No Known Activations