© 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. 12798
    Prev
    Next
    INDEX
    Explanations

    German adjective and noun endings

    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
    liches
    -0.13
    ováno
    -0.11
    aky
    -0.11
    legt
    -0.11
    lichkeit
    -0.10
    âĶĥ
    -0.10
    izzato
    -0.10
    é£
    -0.10
     Suche
    -0.10
    ASA
    -0.09
    POSITIVE LOGITS
    ischen
    0.23
    lichen
    0.23
    igen
    0.19
    uellen
    0.18
    enden
    0.17
    genden
    0.17
    ierten
    0.16
    sten
    0.16
    utschen
    0.15
    iven
    0.13
    Activations Density 0.070%

    No Known Activations