© 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. 62061
    Prev
    Next
    INDEX
    Explanations

    ability to do anything now

    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
    alic
    -0.11
    sian
    -0.09
    umo
    -0.09
    Ð¡Ðł
    -0.09
    SEO
    -0.09
    spb
    -0.08
    ches
    -0.08
     اÙĦخاصة
    -0.08
    ìĿ´ìĸ´
    -0.08
    áze
    -0.08
    POSITIVE LOGITS
    /e
    0.11
     dime
    0.11
    gg
    0.11
    arian
    0.10
     except
    0.10
     desired
    0.10
     asked
    0.10
    ask
    0.09
    THING
    0.09
     necessary
    0.09
    Activations Density 0.031%

    No Known Activations