© 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. 80812
    Prev
    Next
    INDEX
    Explanations

    phrases related to non-discrimination and disability rights

    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
     Pessoa
    -0.09
    eya
    -0.08
    AXB
    -0.08
    agues
    -0.08
    ighter
    -0.08
    abox
    -0.08
    ÄĽk
    -0.08
    SingleOrDefault
    -0.07
    kara
    -0.07
    opak
    -0.07
    POSITIVE LOGITS
     protected
    0.07
     neutral
    0.06
    Protected
    0.06
     Protected
    0.06
     lawful
    0.06
     covered
    0.05
     Gim
    0.05
     intermitt
    0.05
     Neutral
    0.05
     reasonably
    0.05
    Activations Density 0.006%

    No Known Activations