© 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. 19619
    Prev
    Next
    INDEX
    Explanations

    how, why, where, when, whether

    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
     them
    -0.13
    them
    -0.11
    å®ĥ
    -0.11
     him
    -0.10
     ниÑħ
    -0.10
    aina
    -0.10
     mereka
    -0.09
    å®ĥ们
    -0.09
     него
    -0.09
    ä½ł
    -0.09
    POSITIVE LOGITS
    /if
    0.16
    /how
    0.15
     certain
    0.13
    .MixedReality
    0.11
    æł·çļĦ
    0.10
    soever
    0.10
     else
    0.10
    ä¹Ī
    0.09
     mÃł
    0.09
    abouts
    0.09
    Activations Density 0.157%

    No Known Activations