© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 37742
    Prev
    Next
    INDEX
    Explanations

    martial art or fine-tune

    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
    ÐIJÑĢÑħÑĸв
    -0.09
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.09
    anted
    -0.09
     Wolff
    -0.08
    kontakte
    -0.08
    âĦĸâĦĸ
    -0.08
    надлеж
    -0.08
    oon
    -0.08
    lyph
    -0.08
    atest
    -0.08
    POSITIVE LOGITS
    åīĤ
    0.10
    LIKELY
    0.09
     Hund
    0.09
    elin
    0.08
    frei
    0.08
    ubi
    0.08
     Lob
    0.08
     lob
    0.08
    ï¾ŀ
    0.08
    ksam
    0.08
    Activations Density 0.001%

    No Known Activations