© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 8139
    Prev
    Next
    INDEX
    Explanations

    about what "exact"

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases that introduce or frame a topic in explanatory text, especially prepositional lead-ins that set up definitions or specifics.

    oai_token-act-pair · gpt-5
    Triggered by @vetterc0
    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
    Negative Logits
    âĢ³E
    -0.08
    ÌĪ
    -0.08
    .mybatisplus
    -0.07
    ÑĩиÑģл
    -0.07
     æĬķ稿
    -0.07
    .jupiter
    -0.07
    oret
    -0.07
    .renderer
    -0.07
    EditingStyle
    -0.07
     seksi
    -0.07
    POSITIVE LOGITS
    Ｏ
    0.08
     âĶĢ
    0.08
     ï¼ı
    0.08
     поба
    0.08
    pra
    0.07
    .ix
    0.07
     rar
    0.07
    vise
    0.07
    NewProp
    0.07
    aar
    0.07
    Activations Density 0.940%

    No Known Activations