© 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. 53758
    Prev
    Next
    INDEX
    Explanations

    parent/child/base class mappings

    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
     -*-č\n
    -0.10
    ******č\n
    -0.10
    eyse
    -0.10
    inspace
    -0.10
    ToPoint
    -0.09
    ¶Į
    -0.09
    ecko
    -0.09
    IIIK
    -0.09
    ¨ë¶Ģ
    -0.08
    ráž
    -0.08
    POSITIVE LOGITS
     cable
    0.08
    ucha
    0.08
    ATEST
    0.08
    /original
    0.08
    opper
    0.08
    ier
    0.08
    iest
    0.07
    ÙĬÙĬر
    0.07
    -transitional
    0.07
    CHANT
    0.07
    Activations Density 0.094%

    No Known Activations