© 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. 14248
    Prev
    Next
    INDEX
    Explanations

    programming libraries and techniques

    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
     use
    -0.14
     uses
    -0.13
    çĶ¨äºİ
    -0.12
     using
    -0.12
    为äºĨ
    -0.12
     used
    -0.12
    çĶ¨
    -0.11
     gebruik
    -0.11
     uży
    -0.10
    /use
    -0.10
    POSITIVE LOGITS
     techniques
    0.15
     technique
    0.14
     technology
    0.12
     approach
    0.11
     Uns
    0.10
     facilities
    0.10
     alone
    0.10
    technology
    0.10
    ivar
    0.09
     jud
    0.09
    Activations Density 0.200%

    No Known Activations