© 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. 15912
    Prev
    Next
    INDEX
    Explanations

    -it, -dit, -ted, -tion, -tively

    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
    er
    -0.17
    ed
    -0.16
    hand
    -0.15
    hire
    -0.13
    ha
    -0.13
    sWith
    -0.12
    le
    -0.12
    house
    -0.12
    hit
    -0.12
    s
    -0.11
    POSITIVE LOGITS
    hec
    0.14
    ecture
    0.14
    ochond
    0.14
    tee
    0.13
    uary
    0.13
    ting
    0.13
    inerary
    0.13
    ively
    0.12
    ÑĤÑĶ
    0.12
    te
    0.12
    Activations Density 0.123%

    No Known Activations