© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14748
    Prev
    Next
    INDEX
    Explanations

    leading supplier of automotive

    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
    -c
    -0.10
     bitter
    -0.09
     Carter
    -0.09
    ockets
    -0.09
     SEM
    -0.09
    _c
    -0.08
     Carson
    -0.08
    oned
    -0.08
    ÙĪزÙĩ
    -0.08
    itter
    -0.08
    POSITIVE LOGITS
    \tCon
    0.13
     CON
    0.13
     Con
    0.13
     Ðļон
    0.12
    (CON
    0.12
     ãĤ³
    0.12
    CON
    0.12
    .Con
    0.12
    _Con
    0.12
    Con
    0.11
    Activations Density 0.180%

    No Known Activations