© 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. 9644
    Prev
    Next
    INDEX
    Explanations

    was/were + 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
    -0.18
     currently
    -0.15
    now
    -0.13
    /w
    -0.12
    缮åīį
    -0.12
     oldest
    -0.12
     maintenant
    -0.11
     today
    -0.11
     heute
    -0.10
    currently
    -0.10
    POSITIVE LOGITS
     originally
    0.18
    nt
    0.17
    /is
    0.16
     instrumental
    0.15
     eventually
    0.14
     ahead
    0.13
     later
    0.13
     initially
    0.12
     Instrument
    0.12
     redis
    0.12
    Activations Density 0.085%

    No Known Activations