© 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. 32449
    Prev
    Next
    INDEX
    Explanations

    forced or obliged actions

    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
    .Companion
    -0.10
    ICO
    -0.09
     oppressive
    -0.08
    ãĥ³ãĥĸ
    -0.08
     Pace
    -0.08
    652
    -0.08
     Bast
    -0.08
    esson
    -0.08
    ANCELED
    -0.08
     bast
    -0.08
    POSITIVE LOGITS
     forced
    0.66
    forced
    0.58
     Forced
    0.55
    è¿«
    0.44
     buá»Ļc
    0.42
     forcing
    0.41
     compelled
    0.36
    ä¸įå¾Ĺ
    0.35
    forcing
    0.34
     obliged
    0.34
    Activations Density 0.170%

    No Known Activations