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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 34561
    Prev
    Next
    INDEX
    Explanations

    displaying data on screen

    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
    AndView
    -0.09
     cere
    -0.09
    usi
    -0.08
    _DISPATCH
    -0.08
     Oxford
    -0.08
    uti
    -0.08
    adero
    -0.08
     Crab
    -0.08
    InBackground
    -0.08
    åİ
    -0.08
    POSITIVE LOGITS
     screen
    0.14
    screen
    0.10
     lur
    0.09
    InInspector
    0.09
    å±ı
    0.09
     UI
    0.09
    .screen
    0.09
    (Display
    0.09
     clearly
    0.08
    .::
    0.08
    Activations Density 0.122%

    No Known Activations