© 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. 35988
    Prev
    Next
    INDEX
    Explanations

    solve practical problems

    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
     gros
    -0.09
    743
    -0.09
    coder
    -0.09
    夫
    -0.09
    ettle
    -0.09
    cce
    -0.08
     potentially
    -0.08
     shortcut
    -0.08
    raman
    -0.08
    ESA
    -0.08
    POSITIVE LOGITS
     simple
    0.17
     actual
    0.16
     real
    0.15
     projects
    0.15
     exerc
    0.14
     practical
    0.14
     exercises
    0.14
     small
    0.13
     toy
    0.13
    simple
    0.13
    Activations Density 0.073%

    No Known Activations