© 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. 44372
    Prev
    Next
    INDEX
    Explanations

    whether, if, why, when, not

    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
    ya
    -0.09
    scape
    -0.09
     Ih
    -0.09
    anja
    -0.09
     Died
    -0.09
    ãģĤãĤĭ
    -0.08
    lea
    -0.08
    alm
    -0.08
     Millenn
    -0.08
    Ĺı
    -0.08
    POSITIVE LOGITS
     it
    0.12
     оно
    0.12
    ekler
    0.10
    ãģĿãĤĮãģ¯
    0.09
     these
    0.09
     latter
    0.09
    ushima
    0.09
     they
    0.09
    lush
    0.09
     nó
    0.09
    Activations Density 0.156%

    No Known Activations