© 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. 63351
    Prev
    Next
    INDEX
    Explanations

    challenges, dangers, and difficulties

    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
    arkan
    -0.09
    oker
    -0.08
    TC
    -0.08
    é®®
    -0.08
     sadd
    -0.08
    à¤ķरण
    -0.08
    ï½²
    -0.08
    createFrom
    -0.08
     h
    -0.08
    ,
    -0.08
    POSITIVE LOGITS
    cape
    0.12
     của
    0.12
     of
    0.11
    à¸Ĥà¸Ńà¸ĩ
    0.10
     ÏĦηÏĤ
    0.10
    ủa
    0.10
    appings
    0.09
    NewProp
    0.09
     ofApp
    0.09
    ModelError
    0.09
    Activations Density 0.045%

    No Known Activations