© 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. 12744
    Prev
    Next
    INDEX
    Explanations

    we followed by a verb

    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
    让æĪij
    -0.18
     himself
    -0.17
    æĪijçļĦ
    -0.17
    ç»ĻæĪij
    -0.16
     my
    -0.16
     herself
    -0.15
    ç§ģãģ®
    -0.14
     tôi
    -0.13
     meu
    -0.13
     saya
    -0.13
    POSITIVE LOGITS
     ourselves
    0.79
    Ñħодим
    0.34
    ours
    0.33
     ours
    0.32
     our
    0.32
     دارÛĮÙħ
    0.29
     yaptık
    0.28
     мож
    0.26
     avons
    0.26
    æĪij们çļĦ
    0.25
    Activations Density 0.255%

    No Known Activations