© 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. 15-LLAMASCOPE-RES-131K
    11. 85983
    Prev
    Next
    INDEX
    Explanations

    words related to conflict and competition

    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
    ãĢħ
    -0.10
    nya
    -0.10
    rec
    -0.10
    ri
    -0.10
    names
    -0.10
    uly
    -0.09
    na
    -0.09
    zelf
    -0.09
    ly
    -0.08
    soever
    -0.08
    POSITIVE LOGITS
    izer
    0.09
    ously
    0.08
    lete
    0.08
    ization
    0.08
    grams
    0.08
    iro
    0.07
    iros
    0.07
    tainment
    0.07
    pants
    0.07
    tte
    0.07
    Activations Density 0.064%

    No Known Activations