© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 123404
    Prev
    Next
    INDEX
    Explanations

    issues related to guardianship and the impact on individuals and families

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    was
    -0.07
    icast
    -0.07
    Ø´ÙĬ
    -0.06
     à¤īसन
    -0.06
    ibil
    -0.06
     داشت
    -0.06
     mins
    -0.06
    éĢł
    -0.06
    andi
    -0.06
    scheduled
    -0.06
    POSITIVE LOGITS
     often
    0.16
     sometimes
    0.13
     Often
    0.13
    often
    0.13
     usually
    0.13
    Often
    0.12
     souvent
    0.12
     Sometimes
    0.10
    ometimes
    0.10
    Sometimes
    0.10
    Activations Density 0.060%

    No Known Activations