© 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. 47263
    Prev
    Next
    INDEX
    Explanations

    cleaning up spills and applying

    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
    Interpolator
    -0.09
    Sibling
    -0.09
     sibling
    -0.09
     tubes
    -0.09
     Rim
    -0.09
    cea
    -0.09
    uby
    -0.09
    innie
    -0.09
    ansson
    -0.09
    nect
    -0.08
    POSITIVE LOGITS
     contained
    0.19
     contain
    0.19
     cleanup
    0.17
     containment
    0.15
    contain
    0.15
    -contained
    0.15
    leanup
    0.14
     Cleanup
    0.14
     spill
    0.14
    contained
    0.14
    Activations Density 0.016%

    No Known Activations