© 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. 7873
    Prev
    Next
    INDEX
    Explanations

    quality of service

    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
     ble
    -0.10
    dbo
    -0.09
    .vo
    -0.08
    rak
    -0.08
    cai
    -0.08
     trib
    -0.08
    chie
    -0.08
     Elegant
    -0.08
     complimentary
    -0.08
     fullscreen
    -0.08
    POSITIVE LOGITS
     service
    0.23
     excellent
    0.21
     SERVICE
    0.19
     Service
    0.18
    service
    0.16
     poor
    0.16
    _service
    0.16
     Excellent
    0.16
     prompt
    0.15
    Service
    0.15
    Activations Density 0.042%

    No Known Activations