© 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. 46199
    Prev
    Next
    INDEX
    Explanations

    assistant prompts

    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
     WTF
    -0.10
    oppins
    -0.10
     plá
    -0.09
     hits
    -0.09
    crap
    -0.09
     fro
    -0.08
     of
    -0.08
    à¥Ĥà¤ķ
    -0.08
     frequent
    -0.08
    OND
    -0.08
    POSITIVE LOGITS
     Whe
    0.12
     whe
    0.11
    urr
    0.11
    raw
    0.10
    _CPP
    0.10
    umph
    0.10
    Ack
    0.10
    rr
    0.10
    ollo
    0.10
    ree
    0.10
    Activations Density 0.158%

    No Known Activations