© 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. 41539
    Prev
    Next
    INDEX
    Explanations

    reasons why

    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
    851
    -0.09
    INDEX
    -0.08
    ãĤ±ãĥĥãĥĪ
    -0.08
    adel
    -0.08
    .Mapper
    -0.08
    ermen
    -0.08
    .criteria
    -0.07
    ilm
    -0.07
     Thom
    -0.07
    éra
    -0.07
    POSITIVE LOGITS
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.10
    /Dk
    0.10
    quila
    0.09
     religion
    0.09
    tryside
    0.09
    erland
    0.09
    iegel
    0.08
    unami
    0.08
     Islam
    0.08
     renewables
    0.08
    Activations Density 0.530%

    No Known Activations