© 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. 18594
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns associated with individuals or entities

    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
    xdd
    -0.08
    ezi
    -0.08
     grandchildren
    -0.08
    _Tis
    -0.07
    afone
    -0.07
    ngo
    -0.07
    .MixedReality
    -0.07
    resher
    -0.07
    okino
    -0.07
    aders
    -0.07
    POSITIVE LOGITS
     former
    0.09
     partner
    0.08
     friend
    0.08
     collabor
    0.07
    0.07
     mate
    0.07
     bother
    0.07
     brother
    0.07
    ada
    0.07
     ex
    0.07
    Activations Density 0.022%

    No Known Activations