© 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. 11899
    Prev
    Next
    INDEX
    Explanations

    test methods

    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
     Orient
    -0.09
     Coul
    -0.09
     Mell
    -0.09
    ãĥĨãĥ«
    -0.09
    xing
    -0.09
     Prospect
    -0.08
     MOCK
    -0.08
    reh
    -0.08
    experimental
    -0.08
     Victoria
    -0.08
    POSITIVE LOGITS
     test
    0.26
     tests
    0.20
     Test
    0.18
    test
    0.17
    \TestCase
    0.17
    )test
    0.17
    .test
    0.16
    .parametrize
    0.16
     ÑĤеÑģÑĤ
    0.15
    Smoke
    0.15
    Activations Density 0.026%

    No Known Activations