© 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. 18618
    Prev
    Next
    INDEX
    Explanations

    but followed by contrasting clause

    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
     part
    -0.10
    752
    -0.10
    about
    -0.09
    ioni
    -0.09
     ratt
    -0.09
     whether
    -0.09
    irs
    -0.09
    rs
    -0.08
    arf
    -0.08
    eniable
    -0.08
    POSITIVE LOGITS
     ÑģÑĢеди
    0.19
     among
    0.19
     Among
    0.18
    Among
    0.17
    åħ¶ä¸Ń
    0.16
    among
    0.15
     out
    0.15
     none
    0.14
     hands
    0.14
     Of
    0.13
    Activations Density 0.120%

    No Known Activations