© 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. 38466
    Prev
    Next
    INDEX
    Explanations

    the following information

    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
    ¶Į
    -0.13
     -*-č\n
    -0.12
    ·¸
    -0.12
    ¦æĥħ
    -0.10
    .Formatter
    -0.10
    ĮĴ
    -0.10
    ******č\n
    -0.10
    Ľå»º
    -0.10
    ³ç´°
    -0.10
    _________________\n\n
    -0.10
    POSITIVE LOGITS
    0.08
    !--
    0.08
    and
    0.08
    ops
    0.08
    "
    0.07
     underlying
    0.07
     horr
    0.07
    -T
    0.07
    178
    0.07
    856
    0.07
    Activations Density 0.755%

    No Known Activations