© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 36499
    Prev
    Next
    INDEX
    Explanations

    debug and test capabilities

    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
    lify
    -0.10
     Duy
    -0.10
     Vinci
    -0.09
    \grid
    -0.09
     OMIT
    -0.09
    CustomAttributes
    -0.09
    å°Ħ
    -0.09
    iferay
    -0.08
    avir
    -0.08
    ayi
    -0.08
    POSITIVE LOGITS
     prot
    0.18
     debug
    0.18
     debugging
    0.16
    debug
    0.15
    Debug
    0.15
    prot
    0.15
     Debug
    0.15
     Prot
    0.15
     test
    0.14
    _debug
    0.14
    Activations Density 0.109%

    No Known Activations