© 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. 7906
    Prev
    Next
    INDEX
    Explanations

    more, bigger, stronger, closer, determined

    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
    AndUpdate
    -0.10
     Twice
    -0.10
    asm
    -0.10
     Sey
    -0.10
     persist
    -0.10
     twice
    -0.09
    ennen
    -0.09
     Tar
    -0.08
     memor
    -0.08
     vig
    -0.08
    POSITIVE LOGITS
     each
    0.27
     minute
    0.22
    each
    0.22
     cada
    0.20
     Minute
    0.19
     má»Ĺi
    0.19
     chaque
    0.19
     day
    0.18
     every
    0.18
    Minute
    0.17
    Activations Density 0.035%

    No Known Activations