© 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. 63046
    Prev
    Next
    INDEX
    Explanations

    deseases, desires, wish

    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
    erialize
    -0.12
    çĮ®
    -0.09
    hausen
    -0.09
    RTOS
    -0.09
    iment
    -0.09
    piring
    -0.08
     Blake
    -0.08
    çĥĪ
    -0.08
    irim
    -0.08
    iments
    -0.08
    POSITIVE LOGITS
    uellen
    0.11
    ean
    0.11
    aven
    0.10
    van
    0.10
    aper
    0.10
    halb
    0.10
    rics
    0.09
    uell
    0.09
    ollar
    0.09
    AWN
    0.09
    Activations Density 0.016%

    No Known Activations