© 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. 10653
    Prev
    Next
    INDEX
    Explanations

    conjunctions followed by verbs

    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
     be
    -0.25
     was
    -0.18
     باشد
    -0.16
     wasn
    -0.14
     itself
    -0.13
     has
    -0.13
     داشت
    -0.12
     بÙĪد
    -0.11
     been
    -0.11
     byÄĩ
    -0.11
    POSITIVE LOGITS
     are
    0.28
    ávajÃŃ
    0.25
    ujÃŃ
    0.25
    ÅĪujÃŃ
    0.23
    даÑİÑĤ
    0.23
     иÑģполÑĮзÑĥÑİÑĤ
    0.23
    ноÑģÑıÑĤ
    0.22
     دارÙĨد
    0.22
    аÑİÑĤ
    0.21
     aren
    0.21
    Activations Density 0.296%

    No Known Activations