© 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. 24586
    Prev
    Next
    INDEX
    Explanations

    algorithms, symptoms, concepts, media

    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
    ÏĦική
    -0.16
    ική
    -0.13
     italiana
    -0.13
    anship
    -0.13
    她们
    -0.12
     Gim
    -0.11
    еннаÑı
    -0.11
    gebung
    -0.11
    ÃŃtica
    -0.11
    оваÑı
    -0.11
    POSITIVE LOGITS
    amientos
    0.12
    imientos
    0.12
    idos
    0.12
    amentos
    0.12
    azzi
    0.11
    ones
    0.11
    imentos
    0.11
     persistent
    0.11
    izados
    0.10
    éments
    0.10
    Activations Density 0.125%

    No Known Activations