© 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. 8456
    Prev
    Next
    INDEX
    Explanations

    underlying intentions or purpose

    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
     Promise
    -0.10
     unrestricted
    -0.09
    424
    -0.09
     aspiration
    -0.09
     mantra
    -0.09
    ırak
    -0.09
     promise
    -0.09
    pected
    -0.08
    zee
    -0.08
    ippy
    -0.08
    POSITIVE LOGITS
     motives
    0.36
     motive
    0.35
    mot
    0.34
     моÑĤ
    0.33
    Mot
    0.32
     Mot
    0.29
     intentions
    0.29
     goals
    0.29
     motivation
    0.28
     intent
    0.27
    Activations Density 0.173%

    No Known Activations