© 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. 19298
    Prev
    Next
    INDEX
    Explanations

    approaching destination or distress signals

    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
     walk
    -0.12
     walked
    -0.12
     Transportation
    -0.11
     ti
    -0.11
     Ocean
    -0.10
     Tide
    -0.10
     Hod
    -0.10
     walks
    -0.10
     walking
    -0.10
     transportation
    -0.10
    POSITIVE LOGITS
    ADF
    0.12
     hailed
    0.12
    banks
    0.12
     course
    0.11
     radio
    0.11
     punching
    0.11
    å¼ĭ
    0.10
     engines
    0.10
     Banking
    0.10
     Kup
    0.10
    Activations Density 0.048%

    No Known Activations