© 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. 55370
    Prev
    Next
    INDEX
    Explanations

    word formation with suffixes like -ation, -ification

    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
    uncated
    -0.11
    itionally
    -0.11
    culate
    -0.10
    lements
    -0.10
    okable
    -0.10
    ãģļ
    -0.09
    atically
    -0.09
    aciones
    -0.09
    ightly
    -0.09
    ackers
    -0.09
    POSITIVE LOGITS
    ification
    0.15
    ing
    0.14
    itation
    0.13
    ization
    0.13
    ierung
    0.12
    iation
    0.12
    cing
    0.12
    ening
    0.12
    oration
    0.12
    ation
    0.12
    Activations Density 0.183%

    No Known Activations