© 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. 49359
    Prev
    Next
    INDEX
    Explanations

    fraud detection and prevention

    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
    acks
    -0.10
     quo
    -0.09
    izations
    -0.09
     wo
    -0.09
    ioned
    -0.09
     thro
    -0.09
    aus
    -0.09
    ings
    -0.09
    esimal
    -0.09
     numb
    -0.09
    POSITIVE LOGITS
    ulence
    0.20
    ster
    0.20
    alent
    0.20
    sters
    0.19
    ulent
    0.19
    ulant
    0.17
    ULE
    0.16
     committed
    0.15
     attempt
    0.14
     prevention
    0.14
    Activations Density 0.062%

    No Known Activations