© 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. 9168
    Prev
    Next
    INDEX
    Explanations

    mistake correction

    np_acts-logits-general · gemini-2.5-flash-lite

    periods that end sentences or mark the end of complete statements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     Rosenstein
    -0.09
    =YES
    -0.08
     MainAxisAlignment
    -0.08
    aigned
    -0.08
    hetto
    -0.08
     Shame
    -0.08
     offic
    -0.08
    abet
    -0.08
    reactstrap
    -0.08
    .IsNullOr
    -0.08
    POSITIVE LOGITS
     sic
    0.21
     correction
    0.19
     mist
    0.18
    sic
    0.18
    誤
    0.17
     instead
    0.17
     correct
    0.17
     оÑĪиб
    0.16
    误
    0.16
     mistake
    0.15
    Activations Density 0.459%

    No Known Activations