© 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. 40835
    Prev
    Next
    INDEX
    Explanations

    methods for achieving

    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
     probably
    -0.12
     definitely
    -0.10
     mainly
    -0.10
     deline
    -0.10
    Âł
    -0.09
     obviously
    -0.09
     still
    -0.09
    ack
    -0.09
     usually
    -0.09
     helped
    -0.09
    POSITIVE LOGITS
    }elseif
    0.10
     serve
    0.09
    ©©
    0.09
    alach
    0.09
    edenÃŃ
    0.09
    ĴĮ
    0.09
    afort
    0.09
    .openConnection
    0.09
    еÑĢов
    0.09
     Moran
    0.09
    Activations Density 0.121%

    No Known Activations