© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 25323
    Prev
    Next
    INDEX
    Explanations

    old or classic

    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
     modern
    -0.14
    modern
    -0.10
    Modern
    -0.10
    çݰ代
    -0.10
     moderne
    -0.10
     Recent
    -0.10
     Modern
    -0.10
     recently
    -0.09
     moden
    -0.09
    æĸ°çļĦ
    -0.08
    POSITIVE LOGITS
     older
    0.54
     old
    0.43
    older
    0.40
     Older
    0.39
     legacy
    0.36
    old
    0.31
    -old
    0.30
     earlier
    0.30
     ÑģÑĤаÑĢ
    0.30
    æŧ
    0.30
    Activations Density 0.275%

    No Known Activations