© 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. 10680
    Prev
    Next
    INDEX
    Explanations

    thought

    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
    itarian
    -0.11
    _typeof
    -0.11
    ypad
    -0.10
    èĢIJ
    -0.10
    oved
    -0.09
    dent
    -0.09
     Lama
    -0.09
    ationToken
    -0.09
    itel
    -0.09
    нина
    -0.09
    POSITIVE LOGITS
    fully
    0.27
    -pro
    0.24
    fulness
    0.21
    ful
    0.21
     prov
    0.20
    prov
    0.17
    -out
    0.14
     Prov
    0.14
    FULL
    0.14
     shalt
    0.13
    Activations Density 0.016%

    No Known Activations