© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1438
    Prev
    Next
    INDEX
    Explanations

    mobile recharge plans

    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
     Telegraph
    -0.13
     Telecom
    -0.12
     telecom
    -0.12
    arda
    -0.09
     Moon
    -0.09
    ambi
    -0.09
     Mali
    -0.09
     Wifi
    -0.09
     Telephone
    -0.09
     Bluetooth
    -0.09
    POSITIVE LOGITS
     SIM
    0.22
     sim
    0.21
    SIM
    0.19
     plan
    0.18
     plans
    0.17
     Sim
    0.17
     sims
    0.16
     Sims
    0.16
     voice
    0.15
    Sim
    0.14
    Activations Density 0.047%

    No Known Activations