© 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. 37251
    Prev
    Next
    INDEX
    Explanations

    a plan or clear

    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
     Gross
    -0.09
    ï½Ģãĥ½
    -0.09
    ves
    -0.09
     diss
    -0.08
    KeyName
    -0.08
     foresee
    -0.08
     ãĥ¾
    -0.08
     gross
    -0.08
     Sach
    -0.08
    rah
    -0.08
    POSITIVE LOGITS
     plan
    0.36
     Plan
    0.27
    plan
    0.26
     clear
    0.24
    Plan
    0.23
    -plan
    0.23
     PLAN
    0.22
     план
    0.21
     solid
    0.20
    (plan
    0.19
    Activations Density 0.059%

    No Known Activations