© 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. 25729
    Prev
    Next
    INDEX
    Explanations

    artificial holes, trained language, current job

    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
    ©©
    -0.10
    .SEVER
    -0.10
    >NN
    -0.09
    IIIK
    -0.08
    ÂĢÂĢ
    -0.08
    krv
    -0.08
    KeyName
    -0.07
    .EventQueue
    -0.07
    .UnitTesting
    -0.07
    ldkf
    -0.07
    POSITIVE LOGITS
    âĹİ
    0.07
     sice
    0.07
     [...]
    0.07
    notated
    0.07
    :\n
    0.06
    âĢIJ
    0.06
     MagicMock
    0.06
     dese
    0.06
     âĢª
    0.06
    ãģ¾ãģļ
    0.06
    Activations Density 0.303%

    No Known Activations