© 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. 34294
    Prev
    Next
    INDEX
    Explanations

    comparing and comparing ways

    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
    eneg
    -0.11
     compliment
    -0.10
    undo
    -0.09
    æĶ»
    -0.08
     Shen
    -0.08
    ousel
    -0.08
    asma
    -0.08
     Corinth
    -0.08
    cth
    -0.08
    anela
    -0.08
    POSITIVE LOGITS
     comparison
    0.35
     compare
    0.30
     Comparison
    0.30
     Compare
    0.28
    æ¯Ķè¾ĥ
    0.27
     comparisons
    0.26
    Comparison
    0.26
     compares
    0.25
    compare
    0.25
     comparing
    0.24
    Activations Density 0.114%

    No Known Activations