© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35978
    Prev
    Next
    INDEX
    Explanations

    rod is magnet

    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
     evidently
    -0.10
    à¹ĩà¸ķาม
    -0.08
    à¥Įà¤Ł
    -0.08
    rous
    -0.08
     margin
    -0.08
     Mahmoud
    -0.08
    ãĢĢ ãĢĢ ãĢĢ ãĢĢ ãĢĢ ãĢĢ
    -0.08
     fres
    -0.08
    agan
    -0.08
    oser
    -0.08
    POSITIVE LOGITS
     must
    0.46
    must
    0.37
    å¿ħ
    0.35
     phải
    0.34
     Must
    0.32
    Must
    0.32
    ä¸Ģå®ļ
    0.31
     MUST
    0.29
    å¿ħé¡»
    0.29
     å¿ħ
    0.29
    Activations Density 0.114%

    No Known Activations