© 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. 20096
    Prev
    Next
    INDEX
    Explanations

    nostalgic words or words ending in "ical" or "ism"

    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
    AdapterManager
    -0.10
     Hanna
    -0.09
    ãĤ
    -0.09
    .IsNullOr
    -0.08
     Herman
    -0.08
    دÙĩاÛĮ
    -0.08
    /*/
    -0.08
    西çľģ
    -0.08
    á½°
    -0.08
     Anadolu
    -0.08
    POSITIVE LOGITS
    íķĺëĭ¤
    0.12
    ____
    0.10
    ικÏĮÏĤ
    0.09
     Wade
    0.09
    lamak
    0.09
     etmek
    0.09
    owaÄĩ
    0.09
     Wilkinson
    0.08
    ·
    0.08
    \n
    0.08
    Activations Density 0.247%

    No Known Activations