© 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. 14646
    Prev
    Next
    INDEX
    Explanations

    mistake or error

    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
    sell
    -0.10
     Fak
    -0.09
    ::__
    -0.09
    lrt
    -0.08
     Offensive
    -0.08
    azon
    -0.08
    iken
    -0.08
    öy
    -0.08
    isper
    -0.08
    itters
    -0.08
    POSITIVE LOGITS
     mistake
    0.11
     вÑĭвод
    0.11
     abstraction
    0.11
     Fehler
    0.11
     виÑģнов
    0.10
    çļĦäºĭæĥħ
    0.10
     justice
    0.10
     harm
    0.10
     mistakes
    0.10
     vua
    0.10
    Activations Density 0.059%

    No Known Activations