© 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. 52357
    Prev
    Next
    INDEX
    Explanations

    German verb 'ist' and its predicates

    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
     bekan
    -0.15
     aktuellen
    -0.13
     keinen
    -0.12
     benöt
    -0.11
     Verfügung
    -0.11
     kleinen
    -0.10
     groÃŁen
    -0.10
    idon
    -0.10
     dara
    -0.10
     ihn
    -0.10
    POSITIVE LOGITS
    nte
    0.13
     eine
    0.12
     ein
    0.11
     Teil
    0.11
     завиÑģим
    0.10
    umar
    0.10
    anson
    0.09
     ge
    0.09
     die
    0.09
     LAP
    0.09
    Activations Density 0.083%

    No Known Activations