© 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. 27885
    Prev
    Next
    INDEX
    Explanations

    spacecraft hull or structure

    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
    /lic
    -0.09
    å¯Ħ
    -0.09
    arser
    -0.09
    enson
    -0.09
    ova
    -0.08
     covers
    -0.08
    939
    -0.08
    APSHOT
    -0.08
    使
    -0.08
    çĶ
    -0.08
    POSITIVE LOGITS
     contain
    0.17
     sport
    0.17
     sports
    0.16
     includes
    0.16
     bear
    0.16
     include
    0.15
     contains
    0.15
    includes
    0.14
    bear
    0.14
     have
    0.13
    Activations Density 0.121%

    No Known Activations