© 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. 89613
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related forms indicating ownership

    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
    ian
    -0.07
    mp
    -0.06
    oes
    -0.06
    ist
    -0.05
    ile
    -0.05
    rol
    -0.05
     cause
    -0.05
    emo
    -0.05
     res
    -0.05
    901
    -0.05
    POSITIVE LOGITS
    æĺ¯ä¸Ģ个
    0.13
    æĺ¯ä¸Ģ
    0.13
     merupakan
    0.12
    æĺ¯æĪij
    0.12
    æĺ¯ä¸ª
    0.11
    è¿Ļæĺ¯
    0.11
     lÃł
    0.11
     adalah
    0.10
    upakan
    0.09
     æĺ¯
    0.09
    Activations Density 0.027%

    No Known Activations