© 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. 53432
    Prev
    Next
    INDEX
    Explanations

    mission challenges and rocket science

    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
     astronomical
    -0.12
     helicopt
    -0.11
     astronom
    -0.11
     aerial
    -0.10
     Atomic
    -0.10
     mechan
    -0.10
     invent
    -0.10
     atomic
    -0.10
     productivity
    -0.09
    amic
    -0.09
    POSITIVE LOGITS
     mission
    0.27
     missions
    0.22
     Mission
    0.21
    Mission
    0.19
    mission
    0.18
     crew
    0.15
    MISSION
    0.14
    missions
    0.14
     Crew
    0.14
    crew
    0.12
    Activations Density 0.085%

    No Known Activations