© 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. 19382
    Prev
    Next
    INDEX
    Explanations

    paid or free

    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
     Savings
    -0.14
    avings
    -0.11
     Valle
    -0.10
     Discounts
    -0.10
     Pension
    -0.09
     Cumhur
    -0.09
    andest
    -0.09
     misd
    -0.09
    egin
    -0.09
     savings
    -0.09
    POSITIVE LOGITS
     paid
    0.54
    paid
    0.41
     Paid
    0.40
    Paid
    0.40
     pay
    0.39
     paying
    0.37
    -paid
    0.36
     fee
    0.36
    ä»ĺ
    0.34
     charge
    0.32
    Activations Density 0.144%

    No Known Activations