© 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. 3399
    Prev
    Next
    INDEX
    Explanations

    campo de

    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
     herself
    -0.20
     italiana
    -0.18
     gratuita
    -0.18
     pública
    -0.18
     maduras
    -0.16
     اÙĦرÙħزÙĬØ©
    -0.15
     próxima
    -0.14
     españ
    -0.14
     ráp
    -0.14
     polÃŃtica
    -0.14
    POSITIVE LOGITS
     de
    0.12
     himself
    0.12
    ático
    0.12
     koji
    0.12
     коÑĤоÑĢÑĭй
    0.11
    леннÑĭй
    0.10
    ativo
    0.10
    ário
    0.10
     côt
    0.10
     italiano
    0.10
    Activations Density 0.316%

    No Known Activations