© 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. 16705
    Prev
    Next
    INDEX
    Explanations

    words ending in en

    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
    -0.22
    ton
    -0.18
    den
    -0.17
    gen
    -0.16
    ten
    -0.15
    erah
    -0.15
    eria
    -0.14
    te
    -0.14
    cor
    -0.14
    ern
    -0.14
    POSITIVE LOGITS
    ius
    0.15
    esis
    0.14
    afil
    0.14
    omics
    0.13
    ey
    0.13
    vironment
    0.13
    viron
    0.13
    ough
    0.12
    r
    0.12
    GLISH
    0.12
    Activations Density 0.160%

    No Known Activations