© 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. 54432
    Prev
    Next
    INDEX
    Explanations

    database and SQL

    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
    datap
    -0.09
    JAVA
    -0.09
     Dice
    -0.09
     datap
    -0.09
     yerinde
    -0.09
    òi
    -0.09
    _dma
    -0.09
    dfs
    -0.09
    Dice
    -0.08
    IFn
    -0.08
    POSITIVE LOGITS
     database
    0.34
    æķ°æį®åºĵ
    0.27
    database
    0.23
     table
    0.22
     Database
    0.22
     DB
    0.22
     tables
    0.21
    atabase
    0.21
     db
    0.21
    Database
    0.19
    Activations Density 0.086%

    No Known Activations