© 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. 15473
    Prev
    Next
    INDEX
    Explanations

    solved efficiently

    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
    uru
    -0.10
    Logic
    -0.09
     Stanton
    -0.09
    aat
    -0.09
    ï¼Įé»ĺ认
    -0.09
     éļ
    -0.09
    é¹
    -0.09
     Patterson
    -0.09
    emic
    -0.08
    caps
    -0.08
    POSITIVE LOGITS
     unique
    0.15
     UNIQUE
    0.14
     prov
    0.13
     uniqueness
    0.13
    Prov
    0.13
     Unique
    0.13
     uniquely
    0.12
    åĶ¯ä¸Ģ
    0.12
    Unique
    0.12
    prov
    0.12
    Activations Density 0.178%

    No Known Activations