© 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. 32575
    Prev
    Next
    INDEX
    Explanations

    nature of abstract concepts

    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
    ayscale
    -0.10
    rete
    -0.09
     subsystem
    -0.09
    ileged
    -0.09
    844
    -0.08
    æĺĩ
    -0.08
    doctrine
    -0.08
    bour
    -0.08
    Doctrine
    -0.08
    _CONTEXT
    -0.08
    POSITIVE LOGITS
     nature
    0.17
     reality
    0.17
     Nature
    0.15
     how
    0.15
     Reality
    0.12
     caus
    0.12
    nature
    0.12
     agency
    0.12
     identity
    0.11
     ourselves
    0.11
    Activations Density 0.067%

    No Known Activations