© 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. 47573
    Prev
    Next
    INDEX
    Explanations

    input: " :

    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
    ,､
    -0.09
    /goto
    -0.08
    ulfilled
    -0.08
    -lfs
    -0.08
    ?><
    -0.08
    .CompareTag
    -0.08
    bove
    -0.08
     coquine
    -0.08
    argout
    -0.08
    ,:,
    -0.08
    POSITIVE LOGITS
     "
    0.10
    locker
    0.09
     bog
    0.09
     Fry
    0.09
     George
    0.09
    ÎIJ
    0.09
     passive
    0.08
    :
    0.08
     Bog
    0.08
    ãĢ
    0.08
    Activations Density 0.121%

    No Known Activations