© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 22331
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
     ellas
    -0.25
     elles
    -0.22
    她们
    -0.20
    å®ĥ们
    -0.16
     daughters
    -0.13
    áticas
    -0.13
    žila
    -0.13
     sisters
    -0.13
    ÃŃsticas
    -0.12
     однÑĥ
    -0.12
    POSITIVE LOGITS
    μÎŃνοι
    0.25
    ικοί
    0.21
     kteÅĻÃŃ
    0.20
    izados
    0.19
     byli
    0.18
    иÑĤели
    0.17
    Å¡li
    0.17
    teÅĻÃŃ
    0.17
    anlar
    0.16
    stants
    0.16
    Activations Density 0.176%

    No Known Activations