© 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. 38195
    Prev
    Next
    INDEX
    Explanations

    manifest file properties and behavior

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åľ
    -0.11
     Spotlight
    -0.09
     bil
    -0.09
     MOS
    -0.09
    irs
    -0.09
    AILS
    -0.09
    ymes
    -0.09
     Seat
    -0.09
     Conn
    -0.09
     cin
    -0.09
    POSITIVE LOGITS
     manifest
    0.16
    manifest
    0.15
     Manifest
    0.15
     extension
    0.12
    Manifest
    0.11
     icons
    0.11
     declar
    0.10
     chrome
    0.10
     Icons
    0.10
     declared
    0.10
    Activations Density 0.008%

    No Known Activations