© 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. 13217
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by new sentence starters

    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
     denen
    -0.12
     bunları
    -0.10
    “;These
    -0.10
    "These
    -0.10
    аннÑĭе
    -0.10
    ãģĿãĤĮ
    -0.10
    å®ĥ们
    -0.09
     ãĥİ
    -0.09
     them
    -0.09
    orage
    -0.09
    POSITIVE LOGITS
    è¿Ļ个
    0.34
     this
    0.25
     This
    0.23
     ÑįÑĤоÑĤ
    0.22
    this
    0.22
    该
    0.22
     ÐŃÑĤоÑĤ
    0.21
    This
    0.20
     nÃły
    0.19
     ÑįÑĤа
    0.19
    Activations Density 0.153%

    No Known Activations