© 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. 63076
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to personal 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
    ÙĨÚ¯
    -0.08
    edis
    -0.08
    Ł
    -0.07
    overs
    -0.07
    __[
    -0.07
     Fever
    -0.06
    usaha
    -0.06
    idi
    -0.06
    mr
    -0.06
    δη
    -0.06
    POSITIVE LOGITS
     bearings
    0.07
     feet
    0.06
    itespace
    0.06
    uli
    0.06
     hands
    0.06
     eyes
    0.06
     Amph
    0.06
    esson
    0.06
    _own
    0.06
     sights
    0.05
    Activations Density 0.010%

    No Known Activations