© 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. 20833
    Prev
    Next
    INDEX
    Explanations

    early models, decentralized, Portuguese

    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
     adulthood
    -0.10
     kür
    -0.09
     Bour
    -0.08
     Recent
    -0.08
    Recently
    -0.08
     pending
    -0.08
     recently
    -0.08
    agem
    -0.08
    æľĢè¿ij
    -0.08
    BuilderFactory
    -0.08
    POSITIVE LOGITS
     early
    0.86
    early
    0.68
     earliest
    0.64
    æĹ©
    0.61
     Early
    0.56
    Early
    0.55
     sỼm
    0.39
     earlier
    0.37
     ÑĢан
    0.35
     EAR
    0.35
    Activations Density 0.254%

    No Known Activations