© 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. 5387
    Prev
    Next
    INDEX
    Explanations

    technical issues and errors

    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
    Not in Any Lists

    No Comments

    Negative Logits
     disruptions
    -0.09
    jes
    -0.09
    elf
    -0.09
     informed
    -0.08
    .tpl
    -0.08
     infl
    -0.08
    ุà¸Ķ
    -0.08
     disrupting
    -0.08
    Interrupt
    -0.08
    scenario
    -0.08
    POSITIVE LOGITS
     issues
    0.24
    -related
    0.18
     problems
    0.18
     issue
    0.18
     Issues
    0.16
    issues
    0.13
     blues
    0.13
    Issues
    0.13
     problem
    0.13
     gone
    0.13
    Activations Density 0.135%

    No Known Activations