© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33840
    Prev
    Next
    INDEX
    Explanations

    was/were followed by a value or description

    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
     now
    -0.14
     currently
    -0.13
    uzu
    -0.11
    uster
    -0.10
    ãģłãģij
    -0.10
     usually
    -0.09
    çİ°åľ¨
    -0.09
     ÑģейÑĩаÑģ
    -0.09
    omit
    -0.09
    omid
    -0.09
    POSITIVE LOGITS
    nt
    0.27
    /is
    0.24
    abi
    0.19
    /am
    0.17
    nts
    0.16
     originally
    0.15
    ps
    0.15
     recently
    0.15
     jsem
    0.15
     able
    0.13
    Activations Density 0.097%

    No Known Activations