© 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. 9776
    Prev
    Next
    INDEX
    Explanations

    confinement, restriction, captivity

    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
    ãĥ¼ãĥijãĥ¼
    -0.10
     deported
    -0.10
    æĴ
    -0.10
     handshake
    -0.09
     crippled
    -0.09
     expelled
    -0.09
     Jelly
    -0.08
     Hang
    -0.08
    ãĥ¼ãĥĦ
    -0.08
     hang
    -0.08
    POSITIVE LOGITS
     confinement
    0.30
     conf
    0.26
     lock
    0.26
     trapped
    0.25
     confined
    0.25
     locked
    0.24
     imprisonment
    0.22
     captivity
    0.22
     trap
    0.21
     заклÑİÑĩ
    0.21
    Activations Density 0.177%

    No Known Activations