© 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. 60126
    Prev
    Next
    INDEX
    Explanations

    predictor-corrector approximation methods

    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
     Klein
    -0.10
    cy
    -0.10
     racially
    -0.09
    inox
    -0.09
    /respond
    -0.09
    çĮ
    -0.09
    æĢĢ
    -0.09
     bypass
    -0.09
    eldorf
    -0.08
     меÑĢ
    -0.08
    POSITIVE LOGITS
     Run
    0.23
    Run
    0.19
     stiff
    0.16
     RK
    0.15
     schemes
    0.15
     Simpson
    0.15
     scheme
    0.14
     discret
    0.14
     predictor
    0.14
     Predictor
    0.14
    Activations Density 0.059%

    No Known Activations