© 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. 38510
    Prev
    Next
    INDEX
    Explanations

    tall and slender figure or on his head

    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
     twink
    -0.10
    çĶ·æĢ§
    -0.10
     elderly
    -0.10
     yaÅŁlı
    -0.09
     lep
    -0.09
     Adult
    -0.09
     men
    -0.09
     leer
    -0.09
     empt
    -0.09
     purple
    -0.09
    POSITIVE LOGITS
     fre
    0.13
     viv
    0.12
     Wir
    0.11
     girl
    0.10
     tom
    0.10
    ç¬ij
    0.10
     radi
    0.10
    andid
    0.10
     hoy
    0.09
     laugh
    0.09
    Activations Density 0.101%

    No Known Activations