© 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. 46634
    Prev
    Next
    INDEX
    Explanations

    indicates 'this'

    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
    éĤ£æł·
    -0.12
     ê·¸ê²ĥ
    -0.10
     aforementioned
    -0.10
    "These
    -0.09
    “;These
    -0.09
     kia
    -0.09
     ÑĤого
    -0.09
    ï¼ĮéĤ£
    -0.08
    orage
    -0.08
     những
    -0.08
    POSITIVE LOGITS
     this
    0.41
    è¿Ļ个
    0.35
    this
    0.34
     nÃły
    0.30
    \tthis
    0.27
    è¿Ļä¸Ģ
    0.27
     Ùĩذا
    0.26
     dieser
    0.25
    ãģĵãģ®
    0.25
    è¿Ļ
    0.25
    Activations Density 0.208%

    No Known Activations