© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38867
    Prev
    Next
    INDEX
    Explanations

    explaining number variations

    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
     Norm
    -0.09
    ulo
    -0.09
    Theory
    -0.09
     imperson
    -0.09
     Mim
    -0.09
    å¹³åĿĩ
    -0.09
    _drv
    -0.08
    çIJĨ论
    -0.08
    378
    -0.08
     theories
    -0.08
    POSITIVE LOGITS
     figures
    0.15
     definition
    0.14
     counting
    0.14
     data
    0.14
     defin
    0.14
     figure
    0.14
     Definition
    0.14
     exact
    0.14
     sources
    0.13
     definitions
    0.13
    Activations Density 0.109%

    No Known Activations