© 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. 42796
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and apostrophes 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
     Saves
    -0.06
    oki
    -0.06
     other
    -0.06
     staple
    -0.06
     Indeed
    -0.06
    folio
    -0.05
    aldi
    -0.05
    oro
    -0.05
    burger
    -0.05
     favorable
    -0.05
    POSITIVE LOGITS
     theirs
    0.13
     hers
    0.11
     ours
    0.10
     ones
    0.10
    mine
    0.09
     ÑĤоже
    0.09
     version
    0.09
     own
    0.08
     yours
    0.08
    ãĤĤãģ®
    0.08
    Activations Density 0.048%

    No Known Activations