© 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. 62676
    Prev
    Next
    INDEX
    Explanations

    lenguaje

    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
    elor
    -0.10
     ku
    -0.10
    iga
    -0.09
    ocab
    -0.09
    orton
    -0.09
     relic
    -0.09
     accomp
    -0.08
    thew
    -0.08
     Dixon
    -0.08
    ocaly
    -0.08
    POSITIVE LOGITS
    age
    0.13
     spoken
    0.12
     artificial
    0.12
    ibold
    0.11
     natural
    0.11
     machine
    0.10
    illage
    0.10
    auge
    0.10
    è¨Ģ
    0.09
    itude
    0.09
    Activations Density 0.021%

    No Known Activations