© 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. 64923
    Prev
    Next
    INDEX
    Explanations

    in addition or in terms

    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
     anticipation
    -0.11
     tandem
    -0.10
     Farr
    -0.08
    errupted
    -0.08
    ứ
    -0.08
     institution
    -0.08
    deÅŁ
    -0.08
     æĸ¼
    -0.08
     connexion
    -0.08
    iet
    -0.08
    POSITIVE LOGITS
     addition
    0.23
     terms
    0.22
     Addition
    0.15
     recent
    0.14
    terms
    0.13
     additions
    0.13
     TERMS
    0.12
     add
    0.12
     Terms
    0.12
     line
    0.12
    Activations Density 0.008%

    No Known Activations