© 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. 51494
    Prev
    Next
    INDEX
    Explanations

    human or dog

    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
     Current
    -0.11
    Current
    -0.11
     current
    -0.09
    _current
    -0.09
     Premiere
    -0.09
     Prel
    -0.09
    -current
    -0.09
     CURRENT
    -0.08
    usat
    -0.08
     infr
    -0.08
    POSITIVE LOGITS
     earlier
    0.74
     Earlier
    0.50
     previously
    0.48
    Earlier
    0.47
    ä¹ĭåīį
    0.37
    åĪļæīį
    0.34
     previous
    0.31
     ÑĢан
    0.31
     Previously
    0.29
    ear
    0.28
    Activations Density 0.148%

    No Known Activations