© 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. 64920
    Prev
    Next
    INDEX
    Explanations

    Earth's shape

    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
    ise
    -0.09
     Martian
    -0.09
     celestial
    -0.09
     âĸ²
    -0.09
    rs
    -0.09
     Cong
    -0.09
    ivo
    -0.08
    ucci
    -0.08
    ;:;:;:;:
    -0.08
    oucher
    -0.08
    POSITIVE LOGITS
     Ga
    0.12
     home
    0.11
    Ga
    0.11
    ozem
    0.11
     Earth
    0.11
     lith
    0.10
     hosp
    0.10
     breathable
    0.10
     habit
    0.10
     Ear
    0.10
    Activations Density 0.058%

    No Known Activations