© 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. 19707
    Prev
    Next
    INDEX
    Explanations

    typical confines of AI

    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
     Tec
    -0.09
    reesome
    -0.09
    uso
    -0.08
    itech
    -0.08
    elpers
    -0.08
     homeland
    -0.08
    \TestCase
    -0.08
     Num
    -0.08
    ce
    -0.08
    ink
    -0.08
    POSITIVE LOGITS
     limitations
    0.13
     rules
    0.12
     Pandora
    0.11
     reality
    0.11
     AI
    0.10
     typical
    0.10
     limitation
    0.10
    Debe
    0.10
     being
    0.10
     rám
    0.10
    Activations Density 0.050%

    No Known Activations