© 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. 61468
    Prev
    Next
    INDEX
    Explanations

    language, dubbing, foreign films

    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
    longleftrightarrow
    -0.10
     crossover
    -0.10
     sos
    -0.09
     livest
    -0.09
     logos
    -0.08
    ownt
    -0.08
     pronunciation
    -0.08
     NZ
    -0.08
     swallow
    -0.08
     Eag
    -0.08
    POSITIVE LOGITS
     mult
    0.22
     mistr
    0.16
     dub
    0.16
     international
    0.15
     ë²Ī
    0.15
     NSLocalizedString
    0.15
     ç¿
    0.15
     globalization
    0.14
     localize
    0.14
     localized
    0.14
    Activations Density 0.110%

    No Known Activations