© 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. 22168
    Prev
    Next
    INDEX
    Explanations

    word endings and suffixes

    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
    ka
    -0.21
    pro
    -0.20
    bi
    -0.17
    li
    -0.16
    pl
    -0.16
    ba
    -0.16
    va
    -0.16
    ca
    -0.16
    ki
    -0.16
    ÑģÑı
    -0.15
    POSITIVE LOGITS
    Ùĭ
    0.24
    'nın
    0.21
    ’;nın
    0.20
    issance
    0.16
    iah
    0.16
    ient
    0.15
    club
    0.15
    ux
    0.15
    oui
    0.15
    ÙĭØĮ
    0.15
    Activations Density 0.464%

    No Known Activations