© 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. 42122
    Prev
    Next
    INDEX
    Explanations

    legal conditions and rulings

    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
    è¨
    -0.09
    /lic
    -0.09
    MBER
    -0.09
    lus
    -0.08
     lif
    -0.08
    ìn
    -0.08
    lsen
    -0.08
    adm
    -0.08
     Defendants
    -0.08
    ees
    -0.08
    POSITIVE LOGITS
     courts
    0.24
     Courts
    0.15
     court
    0.15
     arg
    0.14
     intent
    0.13
    æ³ķéĻ¢
    0.13
     argue
    0.12
     mere
    0.12
     Arg
    0.12
     under
    0.12
    Activations Density 0.069%

    No Known Activations