© 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. 21903
    Prev
    Next
    INDEX
    Explanations

    extracting facts from text

    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
    pras
    -0.09
     Writes
    -0.09
    ¶Į
    -0.09
    raud
    -0.09
    žel
    -0.09
    beb
    -0.09
    ´:
    -0.09
    eview
    -0.08
     Rencontres
    -0.08
    SharedPointer
    -0.08
    POSITIVE LOGITS
     text
    0.15
     string
    0.11
     input
    0.11
     sentence
    0.10
     contains
    0.10
    æĸĩ
    0.10
     contain
    0.10
     Lem
    0.10
    text
    0.09
     containing
    0.09
    Activations Density 0.317%

    No Known Activations