© 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. 23316
    Prev
    Next
    INDEX
    Explanations

    singular entity identification

    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
     BOTH
    -0.10
     slate
    -0.09
    rippling
    -0.09
     halves
    -0.09
    ite
    -0.09
     Som
    -0.08
    inea
    -0.08
     Mor
    -0.08
    ops
    -0.08
     both
    -0.08
    POSITIVE LOGITS
     one
    0.43
    one
    0.32
     satu
    0.26
    _one
    0.25
    -one
    0.24
     íķĺëĤĺ
    0.23
     each
    0.22
    ä¸Ģ人
    0.22
     одна
    0.22
     однÑĥ
    0.21
    Activations Density 0.145%

    No Known Activations