© 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. 331
    Prev
    Next
    INDEX
    Explanations

    Suffixes like -ção, -ciones, -ura, -ica

    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
    pro
    -0.16
    ka
    -0.14
    va
    -0.13
    pi
    -0.13
    nya
    -0.12
    ba
    -0.12
    ha
    -0.12
    pl
    -0.12
    kin
    -0.12
    pa
    -0.11
    POSITIVE LOGITS
    ux
    0.22
    ção
    0.20
    issance
    0.16
    ledge
    0.16
    ções
    0.15
    udio
    0.14
    Ø©
    0.14
    ÄįnÃŃ
    0.13
    irement
    0.13
    ient
    0.13
    Activations Density 0.156%

    No Known Activations