© 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. 38863
    Prev
    Next
    INDEX
    Explanations

    output in JSON format

    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
     Mason
    -0.08
    adia
    -0.08
    rase
    -0.08
     Higgins
    -0.07
     preca
    -0.07
     #%
    -0.07
    enn
    -0.07
    -âĢIJ
    -0.07
     closeModal
    -0.07
    ijke
    -0.07
    POSITIVE LOGITS
    ulumi
    0.11
    ÂĢÂĢ
    0.10
    ĥ½
    0.10
    andler
    0.09
    NCY
    0.09
    STYPE
    0.08
    umi
    0.08
    imar
    0.08
    iferay
    0.08
     Playoff
    0.08
    Activations Density 0.263%

    No Known Activations