© 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. 38376
    Prev
    Next
    INDEX
    Explanations

    issues addressed or resolved

    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
     amel
    -0.11
     endangered
    -0.10
     threatened
    -0.10
    Affected
    -0.10
     избав
    -0.09
     burden
    -0.09
    affected
    -0.09
     Rid
    -0.09
    ä¿Ŀè¯ģ
    -0.09
    PackageManager
    -0.09
    POSITIVE LOGITS
     addressed
    0.29
     address
    0.22
     dealt
    0.20
     Address
    0.20
     resolved
    0.19
    address
    0.18
    -address
    0.18
     rect
    0.18
     handled
    0.18
    Address
    0.16
    Activations Density 0.087%

    No Known Activations