© 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. 42726
    Prev
    Next
    INDEX
    Explanations

    phrases related to rights and individual ownership issues

    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
    etc
    -0.07
    uzzi
    -0.07
    /gin
    -0.07
    abet
    -0.07
    aise
    -0.07
    ÙĪØŃ
    -0.07
    _ALIGNMENT
    -0.07
    寸
    -0.07
     eiusmod
    -0.07
    emed
    -0.07
    POSITIVE LOGITS
     distinction
    0.13
     distinct
    0.11
     separately
    0.11
     different
    0.11
     separate
    0.11
     distinguished
    0.10
     distinguish
    0.10
     difference
    0.10
     differ
    0.10
     differs
    0.09
    Activations Density 0.042%

    No Known Activations