© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 22193
    Prev
    Next
    INDEX
    Explanations

    end of text marker

    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
    efs
    -0.10
    enz
    -0.09
    asmine
    -0.09
    ake
    -0.08
    ~-~-~-~-
    -0.08
    Ļ¨
    -0.08
    OnInit
    -0.08
    okino
    -0.08
    ãĥ«ãĤ¯
    -0.08
    ói
    -0.08
    POSITIVE LOGITS
     fact
    0.15
     Viá»ĩc
    0.14
     viá»ĩc
    0.13
     presence
    0.13
    fact
    0.12
     having
    0.11
     since
    0.11
    ormal
    0.10
     inclusion
    0.10
     because
    0.10
    Activations Density 0.061%

    No Known Activations