© 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. 58163
    Prev
    Next
    INDEX
    Explanations

    Russian programming and instructions

    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
    .sg
    -0.09
    ánu
    -0.09
    parator
    -0.08
    osas
    -0.08
    opers
    -0.08
    achts
    -0.08
    _Helper
    -0.08
    cona
    -0.08
    ihu
    -0.08
    hap
    -0.08
    POSITIVE LOGITS
    ting
    0.20
    ters
    0.16
    aneous
    0.16
    throat
    0.13
    tings
    0.13
    scenes
    0.12
    cut
    0.12
    -cut
    0.11
    down
    0.11
    icular
    0.11
    Activations Density 0.000%

    No Known Activations