© 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. 63906
    Prev
    Next
    INDEX
    Explanations

    list separators and examples

    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
    .Singleton
    -0.09
     QMainWindow
    -0.08
    tainment
    -0.08
    .twitch
    -0.08
    awaiter
    -0.08
    ellan
    -0.08
     MaterialApp
    -0.08
    âĢ³E
    -0.07
    oto
    -0.07
     Singleton
    -0.07
    POSITIVE LOGITS
    (/^\
    0.09
     roadway
    0.08
    AndWait
    0.08
    =Value
    0.08
    rong
    0.08
     coun
    0.08
    lett
    0.08
    bers
    0.07
    hoo
    0.07
     Coun
    0.07
    Activations Density 0.125%

    No Known Activations