© 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. 25009
    Prev
    Next
    INDEX
    Explanations

    concepts and fields of study

    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
     Laud
    -0.11
     Kern
    -0.09
     Pru
    -0.08
     Bek
    -0.08
    217
    -0.08
    less
    -0.08
     Ipsum
    -0.08
     Laf
    -0.08
     Cum
    -0.08
    ...
    -0.08
    POSITIVE LOGITS
    (åľŁ
    0.10
    ibold
    0.10
     rather
    0.10
     yani
    0.09
    iguous
    0.09
    (íģ¬ê¸°
    0.09
    imens
    0.08
    надлеж
    0.08
     itself
    0.08
     بÙĪدÙĨ
    0.08
    Activations Density 0.414%

    No Known Activations