© 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. 15989
    Prev
    Next
    INDEX
    Explanations

    real returns and performance

    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¸Ńà¸Ń
    -0.10
    åį
    -0.10
    ADB
    -0.09
    inel
    -0.09
     entertaining
    -0.09
    æİĮ
    -0.08
     Inventory
    -0.08
     Chapman
    -0.08
     Hayes
    -0.08
    prediction
    -0.08
    POSITIVE LOGITS
     performance
    0.28
     Performance
    0.24
     returns
    0.24
    performance
    0.23
    Performance
    0.23
     Returns
    0.20
    Returns
    0.20
    returns
    0.20
     PERFORMANCE
    0.19
     performances
    0.19
    Activations Density 0.098%

    No Known Activations