© 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. 13133
    Prev
    Next
    INDEX
    Explanations

    how to do this

    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
     similarly
    -0.10
    zc
    -0.09
    lic
    -0.09
    rox
    -0.09
    urer
    -0.09
     lic
    -0.09
    weise
    -0.09
     Cust
    -0.09
    ÂŃ
    -0.08
    ieg
    -0.08
    POSITIVE LOGITS
     this
    0.27
    this
    0.23
     nÃły
    0.21
     esto
    0.21
     ÑįÑĤо
    0.19
     questo
    0.19
     ÑįÑĤого
    0.17
     Ùĩذا
    0.17
    \tthis
    0.16
     This
    0.16
    Activations Density 0.015%

    No Known Activations