© 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. 34302
    Prev
    Next
    INDEX
    Explanations

    stack operations and balanced parentheses

    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
    OMB
    -0.10
    ouch
    -0.09
    ìĦ
    -0.09
     HBO
    -0.09
     carc
    -0.09
    670
    -0.09
     HB
    -0.09
    omb
    -0.09
     sup
    -0.09
    REE
    -0.08
    POSITIVE LOGITS
     stack
    0.39
     Stack
    0.36
    æł
    0.33
    Stack
    0.31
    stack
    0.30
     push
    0.29
    -stack
    0.29
    .Stack
    0.29
    (stack
    0.28
    .stack
    0.28
    Activations Density 0.047%

    No Known Activations