© 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. 58242
    Prev
    Next
    INDEX
    Explanations

    given variables, list values, amounts, information

    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
    Lists
    -0.12
     fleets
    -0.09
     collabor
    -0.09
     Brennan
    -0.09
     Lists
    -0.09
    TestFixture
    -0.09
     PROFITS
    -0.08
    .lists
    -0.08
    ite
    -0.08
    ify
    -0.08
    POSITIVE LOGITS
    人们
    0.14
     portion
    0.12
     list
    0.12
     ones
    0.11
    bsites
    0.11
    ones
    0.11
    liest
    0.11
    iest
    0.10
    们
    0.10
    åĢij
    0.10
    Activations Density 0.317%

    No Known Activations