© 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. 32216
    Prev
    Next
    INDEX
    Explanations

    occurred, happened, appeared

    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
     поба
    -0.15
     завиÑģим
    -0.12
     ÑģоÑģÑĤавлÑıеÑĤ
    -0.10
    ÑıÑģÑĮ
    -0.10
     диви
    -0.09
    645
    -0.09
    zac
    -0.08
    gart
    -0.08
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.08
     ÙĨدارد
    -0.08
    POSITIVE LOGITS
     occurred
    0.19
     occur
    0.19
     occurs
    0.18
    åıijçĶŁ
    0.18
     xảy
    0.18
     erfol
    0.17
     wurden
    0.17
     happened
    0.15
     happen
    0.15
    æĿ¥äºĨ
    0.15
    Activations Density 0.161%

    No Known Activations