© 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. 60322
    Prev
    Next
    INDEX
    Explanations

    listing characteristics

    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
    à¤ķरण
    -0.09
     cref
    -0.09
    imizer
    -0.08
     failures
    -0.08
    IRMWARE
    -0.08
    /full
    -0.08
    npj
    -0.08
    opes
    -0.08
     promot
    -0.08
    iciálnÃŃ
    -0.08
    POSITIVE LOGITS
     features
    0.51
     characteristics
    0.48
     attributes
    0.44
     traits
    0.43
     aspects
    0.39
     qualities
    0.39
     Features
    0.39
    features
    0.39
     Characteristics
    0.38
    Features
    0.34
    Activations Density 0.411%

    No Known Activations