© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 11626
    Prev
    Next
    INDEX
    Explanations

    inability to retain information

    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
     replica
    -0.11
    criptor
    -0.09
     replicas
    -0.08
     instanceof
    -0.08
    edom
    -0.08
     recurs
    -0.08
     Consum
    -0.08
     depressing
    -0.08
     Cec
    -0.08
     replicate
    -0.08
    POSITIVE LOGITS
     memory
    0.30
     Memory
    0.25
    memory
    0.25
    Memory
    0.23
     remember
    0.21
     기ìĸµ
    0.21
     memories
    0.21
     remembers
    0.20
     carry
    0.20
     MEMORY
    0.19
    Activations Density 0.154%

    No Known Activations