© 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. 10638
    Prev
    Next
    INDEX
    Explanations

    conjunctions and paired concepts

    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
    ãģıãĤĵ
    -0.10
    hort
    -0.09
    :::::::::::::
    -0.09
    ½Ķ
    -0.09
    667
    -0.09
    OPS
    -0.09
     ìłķëıĦ
    -0.08
    .Management
    -0.08
    atürk
    -0.08
    addy
    -0.08
    POSITIVE LOGITS
     detail
    0.13
     control
    0.12
     interest
    0.11
     perspective
    0.11
    /or
    0.11
     support
    0.11
     HO
    0.10
     direction
    0.10
     authority
    0.10
     liv
    0.09
    Activations Density 0.074%

    No Known Activations