© 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. 1949
    Prev
    Next
    INDEX
    Explanations

    descrever algo

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

    phrases that introduce a definition or explanation of a term (often after punctuation like a colon or comma), across multiple languages.

    oai_token-act-pair · gpt-5Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    exampleInput
    -0.08
    also
    -0.08
    exampleInputEmail
    -0.08
     other
    -0.08
    other
    -0.08
     ÑĤакже
    -0.07
     ifndef
    -0.07
    this
    -0.07
    ü
    -0.06
     also
    -0.06
    POSITIVE LOGITS
    ¶Į
    0.09
    ¦æĥħ
    0.09
    lý
    0.08
    podob
    0.08
    ******č\n
    0.08
    Â
    0.08
    ¡°
    0.07
    ³ç´°
    0.07
    raci
    0.07
    Ĥæķ°
    0.07
    Activations Density 2.385%

    No Known Activations