© 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. 20462
    Prev
    Next
    INDEX
    Explanations

    according to legend, philosophy, or belief

    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
    380
    -0.09
    ouri
    -0.09
     Hugo
    -0.09
    formance
    -0.09
     equ
    -0.09
     dut
    -0.09
     fe
    -0.08
     seguint
    -0.08
    andi
    -0.08
     Weinstein
    -0.08
    POSITIVE LOGITS
     sources
    0.14
     records
    0.14
     legend
    0.14
     reports
    0.14
     recent
    0.14
     information
    0.12
     tradition
    0.12
     estimates
    0.12
     latest
    0.12
     calculations
    0.12
    Activations Density 0.052%

    No Known Activations