© 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. 53967
    Prev
    Next
    INDEX
    Explanations

    references to multiple languages and linguistic diversity

    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
    ipo
    -0.07
    AXB
    -0.07
    á»ĥ
    -0.07
    ampo
    -0.06
    νε
    -0.06
    olv
    -0.06
    angelo
    -0.06
    -generation
    -0.06
     misd
    -0.06
     Merk
    -0.06
    POSITIVE LOGITS
     languages
    0.07
    kova
    0.07
     versions
    0.07
    ë³Ħ
    0.07
    ãĥ¼ãĥĦ
    0.06
     Versions
    0.06
    /english
    0.06
     Revel
    0.06
     Americas
    0.06
    itudes
    0.06
    Activations Density 0.016%

    No Known Activations