© 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. 12071
    Prev
    Next
    INDEX
    Explanations

    past participles after 'to be' verbs

    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
     astonished
    -0.10
     accepted
    -0.09
    LEM
    -0.09
     Welch
    -0.09
    oola
    -0.09
     scout
    -0.08
    豪
    -0.08
     excited
    -0.08
    uy
    -0.08
    estroy
    -0.08
    POSITIVE LOGITS
     notified
    0.17
     consulted
    0.15
     loop
    0.14
     present
    0.13
     contacted
    0.12
     thanked
    0.12
     involvement
    0.12
     brought
    0.12
     CC
    0.11
    ÑĢоÑĪ
    0.11
    Activations Density 0.077%

    No Known Activations