© 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. 22391
    Prev
    Next
    INDEX
    Explanations

    non-english characters and symbols

    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
    ÙĪÙĪ
    -0.07
    avr
    -0.07
    oog
    -0.07
    uncios
    -0.07
     Dia
    -0.07
    agna
    -0.07
     makeStyles
    -0.06
    AVE
    -0.06
    avig
    -0.06
     MIC
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    >NN
    0.08
    дÑı
    0.08
    noinspection
    0.08
    anco
    0.07
    âĦĸâĦĸ
    0.07
     (;;)
    0.07
    //{{
    0.07
    -keys
    0.07
    >manual
    0.07
    Activations Density 0.042%

    No Known Activations