© 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. 14633
    Prev
    Next
    INDEX
    Explanations

    limit the amount of memory

    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
    ëį°ìĿ´íĬ¸
    -0.09
     Sphinx
    -0.08
    JECTION
    -0.08
    TOTYPE
    -0.08
    allery
    -0.08
     yıldır
    -0.08
    ìĹĶ
    -0.08
    #
    -0.08
    Adjacent
    -0.08
    lobs
    -0.08
    POSITIVE LOGITS
    èĥ½å¤Ł
    0.08
     inline
    0.08
     Cres
    0.08
     ux
    0.08
    -w
    0.08
     Conn
    0.08
    erne
    0.07
    æĮīçħ§
    0.07
    Conn
    0.07
     comport
    0.07
    Activations Density 0.116%

    No Known Activations