© 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. 51271
    Prev
    Next
    INDEX
    Explanations

    would be, wouldn't for

    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
     ******************************************************************************\n
    -0.10
    _EOL
    -0.10
     foc
    -0.09
    ¶Į
    -0.09
    944
    -0.09
     totally
    -0.09
    ĮĴ
    -0.09
    (er
    -0.09
    ÛĮØ´Ùĩ
    -0.08
     intim
    -0.08
    POSITIVE LOGITS
    ¨
    0.09
    ómo
    0.09
     whom
    0.08
     entirety
    0.08
     Majority
    0.08
     overtime
    0.08
    ubit
    0.08
     HQ
    0.08
     uh
    0.08
    rán
    0.08
    Activations Density 0.344%

    No Known Activations