© 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. 20990
    Prev
    Next
    INDEX
    Explanations

    words ending in ay

    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
    spr
    -0.15
    sy
    -0.13
    sch
    -0.12
    s
    -0.12
    sp
    -0.11
    sa
    -0.11
    sn
    -0.11
    er
    -0.11
    sun
    -0.11
    sx
    -0.11
    POSITIVE LOGITS
    yyyy
    0.22
    urved
    0.19
    yyy
    0.16
    ÑĤеÑģÑĮ
    0.16
    ev
    0.15
    yy
    0.15
    eur
    0.15
    enne
    0.15
    den
    0.15
    YYYY
    0.14
    Activations Density 0.099%

    No Known Activations