© 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. 25029
    Prev
    Next
    INDEX
    Explanations

    order, ordering, ordnung, ordner

    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
    erk
    -0.12
    eries
    -0.12
    eros
    -0.12
    eria
    -0.12
    era
    -0.11
    eral
    -0.11
    rze
    -0.11
    erie
    -0.10
    ERAL
    -0.10
    asting
    -0.10
    POSITIVE LOGITS
    nung
    0.20
    oliberal
    0.17
    inary
    0.15
    inals
    0.15
    ained
    0.14
    ination
    0.13
    entlich
    0.13
    inar
    0.13
    liness
    0.13
    inate
    0.12
    Activations Density 0.031%

    No Known Activations