© 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. 21382
    Prev
    Next
    INDEX
    Explanations

    performing well and selling

    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
     поба
    -0.11
     Highly
    -0.10
    İ·
    -0.08
    æĽ´åĬł
    -0.08
     зави
    -0.08
     cleanly
    -0.08
     sufficiently
    -0.08
    ollo
    -0.08
    eller
    -0.08
    _QUAL
    -0.08
    POSITIVE LOGITS
     well
    0.68
    well
    0.49
     ÑħоÑĢоÑĪо
    0.43
     dobÅĻe
    0.41
     Well
    0.39
     WELL
    0.38
     bien
    0.37
    Well
    0.37
     better
    0.32
     poorly
    0.32
    Activations Density 0.195%

    No Known Activations