© 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. 53362
    Prev
    Next
    INDEX
    Explanations

    very long time ago

    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
    745
    -0.11
     lifelong
    -0.10
    790
    -0.09
    lingen
    -0.08
    ::|
    -0.08
    abal
    -0.08
    .DataTable
    -0.08
     å»
    -0.08
    (___
    -0.08
    icker
    -0.08
    POSITIVE LOGITS
     long
    0.50
     давно
    0.33
    long
    0.31
     ago
    0.29
     dáv
    0.27
     LONG
    0.25
    ä¹ħ
    0.25
    (long
    0.25
     years
    0.24
     hace
    0.24
    Activations Density 0.195%

    No Known Activations