© 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. 63119
    Prev
    Next
    INDEX
    Explanations

    references to bilingualism and heritage language use

    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
    aga
    -0.07
    loor
    -0.07
    ?action
    -0.07
     Twice
    -0.07
    _ALIGNMENT
    -0.07
    .met
    -0.06
     Gül
    -0.06
    ÑĢон
    -0.06
    uur
    -0.06
     krb
    -0.06
    POSITIVE LOGITS
    -switch
    0.08
     Acquisition
    0.07
     acquisition
    0.07
     nat
    0.06
     spoken
    0.06
     switching
    0.06
    ìĸ¸
    0.06
     language
    0.06
     flu
    0.06
     pressure
    0.06
    Activations Density 0.013%

    No Known Activations