© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 28122
    Prev
    Next
    INDEX
    Explanations

    amount and percentage

    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
    æĭ©
    -0.10
     sposób
    -0.10
     Bac
    -0.10
     Fah
    -0.09
     Zd
    -0.09
    rain
    -0.08
     pitch
    -0.08
    лÑıÑħ
    -0.08
    ablish
    -0.08
     emph
    -0.08
    POSITIVE LOGITS
    å¤ļå°ij
    0.41
     ÑģколÑĮко
    0.33
    ितन
    0.30
     how
    0.27
     ìĸ¼ë§Ī
    0.26
     amount
    0.24
     nhiêu
    0.23
     How
    0.22
    how
    0.21
     kaç
    0.20
    Activations Density 0.162%

    No Known Activations