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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43786
    Prev
    Next
    INDEX
    Explanations

    prioritize one's, show them, preparing for

    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
     either
    -0.10
    either
    -0.09
    âĢķâĢķâĢķâĢķ
    -0.09
     nejen
    -0.09
    -,
    -0.08
    ~/
    -0.08
     både
    -0.08
    NotEmpty
    -0.07
    ikan
    -0.07
    olas
    -0.07
    POSITIVE LOGITS
     certain
    0.10
     addCriterion
    0.08
     etc
    0.08
     voc
    0.08
     SOME
    0.08
    UMB
    0.08
     initially
    0.08
    æŁIJ
    0.08
     Hüs
    0.07
    ODY
    0.07
    Activations Density 0.030%

    No Known Activations