Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65394
    Prev
    Next
    INDEX
    Explanations

    concepts followed by 'that'

    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
     ÏĢÏīÏĤ
    -0.10
     vis
    -0.10
    angu
    -0.09
    mbH
    -0.09
     for
    -0.09
    .
    -0.09
    umi
    -0.09
    argon
    -0.08
    allon
    -0.08
    aint
    -0.08
    POSITIVE LOGITS
     that
    0.13
     ÏĢοÏħ
    0.12
     which
    0.11
     yang
    0.10
     hat
    0.09
    which
    0.09
     коÑĤоÑĢаÑı
    0.09
     qui
    0.09
    that
    0.09
     whose
    0.09
    Activations Density 0.134%

    No Known Activations