© 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. 31532
    Prev
    Next
    INDEX
    Explanations

    negations and qualifications in statements

    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
     itself
    -0.24
     its
    -0.14
     Ñıке
    -0.12
     Its
    -0.12
    æĺ¯ä¸Ģ个
    -0.10
    Its
    -0.10
    å®ĥ
    -0.09
     коÑĤоÑĢое
    -0.09
    æĺ¯ä¸ª
    -0.09
     jehož
    -0.09
    POSITIVE LOGITS
     themselves
    0.27
     thems
    0.13
    ones
    0.12
     ones
    0.12
     коÑĤоÑĢÑĭе
    0.12
     their
    0.11
    Their
    0.11
     are
    0.11
    their
    0.11
     Their
    0.10
    Activations Density 2.208%

    No Known Activations