© 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. 46048
    Prev
    Next
    INDEX
    Explanations

    the [quality] of the [thing]

    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
     fate
    -0.12
    ansa
    -0.09
     richtig
    -0.09
     length
    -0.08
    eker
    -0.08
    abin
    -0.08
     duration
    -0.08
     ende
    -0.08
     Fate
    -0.08
     Verfüg
    -0.08
    POSITIVE LOGITS
    ses
    0.17
     particular
    0.16
     underlying
    0.13
     specific
    0.10
    ãĥªãĤ«
    0.10
     beast
    0.09
    illac
    0.09
     overall
    0.09
     chosen
    0.09
     individual
    0.09
    Activations Density 0.076%

    No Known Activations