© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37725
    Prev
    Next
    INDEX
    Explanations

    feel at this time

    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
     remembered
    -0.10
     ï½ľ
    -0.09
    说è¯Ŀ
    -0.09
     Speaking
    -0.09
     speaking
    -0.09
    451
    -0.08
    oba
    -0.08
    arend
    -0.08
    Speaking
    -0.08
    Ãij
    -0.08
    POSITIVE LOGITS
     hearing
    0.40
    åIJ¬åĪ°
    0.28
     Hearing
    0.27
     seeing
    0.24
     upon
    0.24
     news
    0.24
     hear
    0.22
     learning
    0.21
     receiving
    0.21
     heard
    0.20
    Activations Density 0.177%

    No Known Activations