© 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. 46118
    Prev
    Next
    INDEX
    Explanations

    certain circumstances

    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
     tutte
    -0.10
     вÑģеÑħ
    -0.10
     semua
    -0.09
     todas
    -0.09
     todos
    -0.09
     ï¾ŀ
    -0.09
     qualquer
    -0.09
     toutes
    -0.08
    ugo
    -0.08
     všech
    -0.08
    POSITIVE LOGITS
     certain
    0.91
     Certain
    0.69
    Certain
    0.61
     certains
    0.58
    æŁIJ
    0.52
    ertain
    0.47
     bestimm
    0.46
     some
    0.40
     select
    0.37
     selected
    0.33
    Activations Density 0.231%

    No Known Activations