© 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. 63194
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts and public disputes

    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
    chwitz
    -0.08
    ÑĢаниÑĨ
    -0.07
    isor
    -0.07
    ноÑĪ
    -0.06
    linger
    -0.06
    atak
    -0.06
    akan
    -0.06
    azar
    -0.06
    å¬
    -0.06
    iale
    -0.06
    POSITIVE LOGITS
     when
    0.14
    when
    0.11
     quando
    0.10
     lorsque
    0.10
     cuando
    0.10
     When
    0.10
     عÙĨدÙħا
    0.10
    _when
    0.10
     WHEN
    0.10
    When
    0.09
    Activations Density 0.130%

    No Known Activations