© 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. 116362
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and words indicating familial relationships

    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
    abela
    -0.08
    urat
    -0.07
    åķ
    -0.07
    udo
    -0.07
    InBackground
    -0.06
    iac
    -0.06
    /Branch
    -0.06
    ozÃŃ
    -0.06
    arov
    -0.06
    arias
    -0.06
    POSITIVE LOGITS
     partner
    0.07
    partner
    0.07
     Citadel
    0.07
     partners
    0.06
     wife
    0.06
    妻
    0.06
    _partner
    0.06
    uire
    0.06
    hol
    0.06
     cuckold
    0.06
    Activations Density 0.001%

    No Known Activations