© 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. 31576
    Prev
    Next
    INDEX
    Explanations

    adverbs of manner

    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
    istrovstvÃŃ
    -0.10
    룴
    -0.10
    ored
    -0.09
    ssp
    -0.09
    CAA
    -0.09
     Fle
    -0.09
    §è¡Į
    -0.09
    isi
    -0.09
    oret
    -0.08
     indirect
    -0.08
    POSITIVE LOGITS
    ursively
    0.18
    ойно
    0.17
    istically
    0.14
    ленно
    0.13
    aneously
    0.12
    르ê²Į
    0.12
    ensively
    0.12
    оÑĩно
    0.11
    Ñĸйно
    0.11
    ÑĢеменно
    0.11
    Activations Density 0.056%

    No Known Activations