© 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. 28467
    Prev
    Next
    INDEX
    Explanations

    foreign language fragments

    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
    a
    -0.21
    o
    -0.16
    i
    -0.14
    es
    -0.13
    aos
    -0.13
    aç
    -0.11
    aes
    -0.11
    aN
    -0.11
    e
    -0.11
    aÄįnÃŃ
    -0.10
    POSITIVE LOGITS
    roscope
    0.09
    ocha
    0.09
    æŀľ
    0.09
    iar
    0.09
    resh
    0.09
    ming
    0.08
    ook
    0.08
    รà¸ĩ
    0.08
    pid
    0.08
    ores
    0.08
    Activations Density 0.247%

    No Known Activations