© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 42338
    Prev
    Next
    INDEX
    Explanations

    Java integer addition

    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
     const
    -0.14
     NULL
    -0.14
    NULL
    -0.13
     Westminster
    -0.12
    =NULL
    -0.11
     self
    -0.11
     str
    -0.11
    (bool
    -0.10
    ::::::::::::::
    -0.10
     Null
    -0.10
    POSITIVE LOGITS
     System
    0.23
     Math
    0.20
    System
    0.19
     Integer
    0.18
    \tSystem
    0.16
    .java
    0.16
    (System
    0.15
    (Integer
    0.15
     Double
    0.14
     java
    0.14
    Activations Density 0.065%

    No Known Activations