© 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. 16071
    Prev
    Next
    INDEX
    Explanations

    first-person past tense narratives

    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
    rou
    -0.10
     teaching
    -0.09
    дем
    -0.09
    ads
    -0.08
     меÑĤалли
    -0.08
    olog
    -0.08
    æĭĽ
    -0.08
     enslaved
    -0.08
    umar
    -0.08
     Underground
    -0.08
    POSITIVE LOGITS
     under
    0.27
     dÆ°á»Ľi
    0.19
     learn
    0.19
     تØŃت
    0.18
     learning
    0.17
     receiving
    0.16
     learns
    0.16
     bajo
    0.16
     Learn
    0.16
     пÑĸд
    0.15
    Activations Density 0.101%

    No Known Activations