© 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. 488
    Prev
    Next
    INDEX
    Explanations

    this/these followed by words or context

    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
    å®ĥ们
    -0.11
     ê·¸ê²ĥ
    -0.10
    ï¼Įæľ¬
    -0.09
     ä»Ĭ
    -0.09
    ãĢģãģĿãĤĮ
    -0.09
    éĤ£æł·
    -0.09
    ä»Ĭ
    -0.09
    ãĢĤæľ¬
    -0.09
    “;These
    -0.08
    \n
    -0.08
    POSITIVE LOGITS
     this
    0.57
    è¿Ļ个
    0.55
     nÃły
    0.50
    this
    0.46
    è¿Ļç§į
    0.45
    è¿Ļä¸Ģ
    0.44
     these
    0.42
    éĢĻ
    0.38
     dieser
    0.38
     acest
    0.38
    Activations Density 0.492%

    No Known Activations