© 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. 25111
    Prev
    Next
    INDEX
    Explanations

    higher temperature

    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
    860
    -0.10
    ãĢ
    -0.10
    enne
    -0.09
    opic
    -0.09
     Ober
    -0.09
    ati
    -0.09
    imit
    -0.09
     Humb
    -0.08
    istingu
    -0.08
    ابت
    -0.08
    POSITIVE LOGITS
     higher
    0.26
    higher
    0.22
     larger
    0.22
     Higher
    0.21
     bigger
    0.20
    Higher
    0.19
     generally
    0.18
     vyÅ¡Å¡ÃŃ
    0.16
     Generally
    0.16
     greater
    0.16
    Activations Density 0.083%

    No Known Activations