© 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
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1329
    Prev
    Next
    INDEX
    Explanations

    "I've fallen" or "tasty treat"

    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
    .lng
    -0.09
    .Disclaimer
    -0.08
    à¸Ļà¸Ń
    -0.08
    taj
    -0.07
    -w
    -0.07
    à¹ĭ
    -0.07
    à¸Ļà¸ģ
    -0.07
    à§į
    -0.07
    cul
    -0.07
    zw
    -0.07
    POSITIVE LOGITS
     tane
    0.08
     Ulus
    0.08
     VÅ¡ech
    0.08
    loit
    0.07
    innamon
    0.07
    hores
    0.07
    .Mutable
    0.07
     MainAxisAlignment
    0.07
    ismet
    0.07
    -CP
    0.07
    Activations Density 0.003%

    No Known Activations