© 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. 31067
    Prev
    Next
    INDEX
    Explanations

    planning and strengthened

    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
     clam
    -0.10
    ìŁģ
    -0.09
     appreh
    -0.09
     bons
    -0.08
    antz
    -0.08
    æĵ
    -0.08
     offic
    -0.08
     Pension
    -0.08
    urgeon
    -0.08
     flare
    -0.08
    POSITIVE LOGITS
     plan
    0.38
     planning
    0.35
     plans
    0.32
     плани
    0.27
    plan
    0.27
    计åĪĴ
    0.26
     Planning
    0.26
     planned
    0.25
     hatch
    0.25
    -plan
    0.25
    Activations Density 0.082%

    No Known Activations