© 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. 38596
    Prev
    Next
    INDEX
    Explanations

    audience, progress, obstacles, results, research

    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
     :\n\n\n\n
    -0.09
     --
    -0.09
    пÑĢимеÑĢ
    -0.07
    ={},
    -0.07
    å¦Ĥä¸ĭ
    -0.07
    à¥ĩà¤Ĥ,
    -0.07
    ..\n\n\n\n
    -0.07
    รà¸Ħ
    -0.07
    ulum
    -0.07
     ,
    -0.07
    POSITIVE LOGITS
    .SuspendLayout
    0.10
     ков
    0.09
    @nate
    0.09
     nowrap
    0.08
    avana
    0.07
    âħ¥
    0.07
    oney
    0.07
    ãģĹãģªãģĦ
    0.07
    .dart
    0.07
    jspx
    0.07
    Activations Density 0.186%

    No Known Activations