© 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. 35685
    Prev
    Next
    INDEX
    Explanations

    retaining names in memory

    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
    -animation
    -0.09
    -hidden
    -0.09
    732
    -0.09
     Lor
    -0.09
     Strom
    -0.08
     pen
    -0.08
    /pub
    -0.08
     Hannah
    -0.08
     alphabet
    -0.08
     uz
    -0.08
    POSITIVE LOGITS
     memory
    0.22
    åį°
    0.22
     stuck
    0.21
     burned
    0.21
     et
    0.20
     impressed
    0.19
     memoria
    0.18
     stick
    0.18
     fresh
    0.17
     sticks
    0.17
    Activations Density 0.097%

    No Known Activations