© 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. 5895
    Prev
    Next
    INDEX
    Explanations

    expressions of possession or 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
    alink
    -0.08
    TestFixture
    -0.08
    olio
    -0.08
    elib
    -0.08
    plication
    -0.08
    ãĥ³ãĤº
    -0.08
    اÙĩÙħ
    -0.08
    .scalablytyped
    -0.07
    обов
    -0.07
    Æ°á»Ľng
    -0.07
    POSITIVE LOGITS
     personally
    0.09
     personal
    0.07
     priv
    0.06
     elsewhere
    0.06
     already
    0.06
     Mond
    0.06
    zz
    0.06
     form
    0.06
    priv
    0.06
     hear
    0.06
    Activations Density 0.025%

    No Known Activations