© 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. 32676
    Prev
    Next
    INDEX
    Explanations

    prison sentences and fines

    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
     prosecutions
    -0.11
     punct
    -0.11
     prosecute
    -0.10
     prosecuted
    -0.10
     rout
    -0.10
     prosecution
    -0.10
    thy
    -0.10
     Moj
    -0.09
     jails
    -0.09
    wards
    -0.09
    POSITIVE LOGITS
     sentence
    0.22
     suspended
    0.19
     sentences
    0.19
    sentence
    0.17
     served
    0.17
     term
    0.17
     serve
    0.16
     Sentence
    0.15
     ÑģÑĢок
    0.15
     Susp
    0.15
    Activations Density 0.028%

    No Known Activations