© 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. 27147
    Prev
    Next
    INDEX
    Explanations

    in [context], the

    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
     à¤ĩसम
    -0.10
    'gc
    -0.09
    printStats
    -0.09
     rằng
    -0.08
     nhau
    -0.08
    AJOR
    -0.08
    YA
    -0.08
    ADIUS
    -0.08
     ÏĮÏĦι
    -0.08
    bd
    -0.08
    POSITIVE LOGITS
     there
    0.14
     we
    0.13
    å°¤
    0.12
    there
    0.10
     especially
    0.10
     íĬ¹íŀĪ
    0.10
     olduÄŁu
    0.10
     particularly
    0.10
     yani
    0.09
    æĿ¥è¯´
    0.09
    Activations Density 0.099%

    No Known Activations