© 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. 42171
    Prev
    Next
    INDEX
    Explanations

    considering investment or purchase

    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
     fitted
    -0.09
     Biz
    -0.09
     Garr
    -0.09
     Christie
    -0.09
     fetched
    -0.09
    odu
    -0.09
     pups
    -0.09
     Kendall
    -0.08
    sher
    -0.08
     Inventory
    -0.08
    POSITIVE LOGITS
     invest
    0.40
     investing
    0.36
     investments
    0.34
     invested
    0.34
     investment
    0.32
    æĬķèµĦ
    0.27
     Invest
    0.27
     Investing
    0.25
     инвеÑģÑĤи
    0.23
    invest
    0.23
    Activations Density 0.097%

    No Known Activations