© 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. 18768
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating relationships and familial connections

    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
     we
    -0.08
     wife
    -0.06
     husband
    -0.06
    æĪijåĢij
    -0.06
    å·±
    -0.06
    æĪij们
    -0.06
    esty
    -0.06
    ones
    -0.06
     Pert
    -0.06
     Solo
    -0.06
    POSITIVE LOGITS
     mutual
    0.10
    åħ±åIJĮ
    0.09
     mutually
    0.08
    ahy
    0.08
    ubble
    0.08
    ä¸Ģèµ·
    0.08
    Together
    0.08
     joint
    0.08
    iyah
    0.08
     ConnectionState
    0.07
    Activations Density 0.032%

    No Known Activations