© 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. 12315
    Prev
    Next
    INDEX
    Explanations

    prepare, ready, preparation, wore, just, to, use

    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
    .:.:.:.:.:.:.:.:
    -0.09
     onCancelled
    -0.09
     BorderRadius
    -0.09
     tête
    -0.08
    æĽ
    -0.08
    ogo
    -0.08
     Nik
    -0.08
    /auto
    -0.08
    apter
    -0.08
     SOS
    -0.08
    POSITIVE LOGITS
     ready
    0.21
     prepar
    0.19
     preparation
    0.17
    åĩĨå¤ĩ
    0.17
     preparing
    0.16
     prepare
    0.16
     Ready
    0.16
     prep
    0.15
     prepares
    0.15
    æºĸ
    0.15
    Activations Density 0.057%

    No Known Activations