© 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. 103854
    Prev
    Next
    INDEX
    Explanations

    instances of the word "generous" or its variants, indicating a focus on the concept of generosity

    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
    _DEFINE
    -0.08
    oggler
    -0.08
    اÙĨÙĪÙĨ
    -0.08
    statt
    -0.08
    .RightToLeft
    -0.08
    enÃŃm
    -0.07
    si
    -0.07
    ttp
    -0.07
    sworth
    -0.07
    uien
    -0.07
    POSITIVE LOGITS
    ately
    0.08
    ously
    0.07
    antly
    0.07
     enough
    0.07
    mente
    0.07
    amente
    0.07
    ess
    0.06
    ity
    0.06
    osity
    0.06
    -hearted
    0.06
    Activations Density 0.004%

    No Known Activations