© 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. 21980
    Prev
    Next
    INDEX
    Explanations

    past participles and connectors

    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
    923
    -0.12
     milit
    -0.10
    ãĤ£
    -0.10
    éĺ
    -0.09
     orthodox
    -0.09
     penet
    -0.09
     aup
    -0.09
    eger
    -0.08
     Bella
    -0.08
     خارجÙĬØ©
    -0.08
    POSITIVE LOGITS
     způsobem
    0.10
     enf
    0.10
     posterior
    0.09
    abyrin
    0.09
    ukan
    0.09
     manual
    0.09
    ivamente
    0.09
    олÑĮно
    0.08
    ativ
    0.08
     sist
    0.08
    Activations Density 0.165%

    No Known Activations