© 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. 11666
    Prev
    Next
    INDEX
    Explanations

    things that come first

    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
    _ISR
    -0.09
    828
    -0.09
    inka
    -0.09
    opup
    -0.09
    borg
    -0.09
     Gat
    -0.09
    InitialState
    -0.08
     debuted
    -0.08
    /false
    -0.08
     Primer
    -0.08
    POSITIVE LOGITS
     first
    0.62
    first
    0.50
     primero
    0.37
    åħĪ
    0.36
     먼ìłĢ
    0.35
     primeiro
    0.33
    .first
    0.33
     eerste
    0.31
     pierws
    0.30
    _first
    0.30
    Activations Density 0.166%

    No Known Activations