© 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. 59357
    Prev
    Next
    INDEX
    Explanations

    that + subject/clause

    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
    isha
    -0.10
     humanity
    -0.09
    ynos
    -0.09
     поÑĤомÑĥ
    -0.08
    ço
    -0.08
     towards
    -0.08
    ystack
    -0.08
     Mild
    -0.08
     according
    -0.08
     geom
    -0.08
    POSITIVE LOGITS
     sometimes
    0.25
     Sometimes
    0.24
    Sometimes
    0.22
    sometimes
    0.21
    ometimes
    0.17
     иногда
    0.16
     bazen
    0.14
    OMET
    0.13
     appearances
    0.12
     true
    0.12
    Activations Density 0.048%

    No Known Activations