© 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. 12207
    Prev
    Next
    INDEX
    Explanations

    managing things

    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
    ÑĮеÑĢ
    -0.08
    ulus
    -0.08
    267
    -0.08
     âĨĵ
    -0.08
    illos
    -0.08
    ande
    -0.08
    engo
    -0.08
    umb
    -0.08
    ables
    -0.08
    åĪ
    -0.08
    POSITIVE LOGITS
     things
    0.91
     Things
    0.70
    things
    0.68
    Things
    0.66
     cosas
    0.48
    äºĭæĥħ
    0.48
     matters
    0.45
     vÄĽci
    0.42
     thing
    0.36
     choses
    0.35
    Activations Density 0.140%

    No Known Activations