© 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. 35996
    Prev
    Next
    INDEX
    Explanations

    german noun endings like -ung, -ungen

    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
    nech
    -0.11
    anzeigen
    -0.11
    idal
    -0.10
    clist
    -0.10
    elli
    -0.10
    atische
    -0.10
    benh
    -0.09
    -wsj
    -0.09
    gett
    -0.09
    orary
    -0.09
    POSITIVE LOGITS
    ung
    0.28
    ings
    0.21
    ungs
    0.21
    ungen
    0.20
    UNG
    0.18
    zung
    0.16
    INGS
    0.16
    ning
    0.14
    igung
    0.12
     ung
    0.12
    Activations Density 0.084%

    No Known Activations