© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 5590
    Prev
    Next
    INDEX
    Explanations

    're/were the one

    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
    Negative Logits
    ä½łä»¬
    -0.10
    845
    -0.09
     Cath
    -0.09
    imas
    -0.09
     ÏĥαÏĤ
    -0.09
     ourselves
    -0.09
    tsy
    -0.09
    ãĢĢï½
    -0.08
    msp
    -0.08
    bios
    -0.08
    POSITIVE LOGITS
    æĪijçļĦ
    0.16
     my
    0.15
     whom
    0.14
     mine
    0.14
     ir
    0.13
     everything
    0.12
     meu
    0.12
     minha
    0.12
     mijn
    0.11
    everything
    0.11
    Activations Density 0.073%

    No Known Activations