© 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. 60674
    Prev
    Next
    INDEX
    Explanations

    natural | colors

    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
     Nut
    -0.09
    Nut
    -0.09
    ovy
    -0.09
    ERP
    -0.08
     reporting
    -0.08
     Dol
    -0.08
    öst
    -0.08
    ARIO
    -0.08
     Nose
    -0.08
    меÑĤÑĮ
    -0.08
    POSITIVE LOGITS
     natural
    0.68
    natural
    0.55
    èĩªçĦ¶
    0.54
     Natural
    0.53
    Natural
    0.48
     natur
    0.45
     doÄŁal
    0.42
     ìŀIJìĹ°
    0.40
     пÑĢиÑĢод
    0.40
    atural
    0.39
    Activations Density 0.165%

    No Known Activations