© 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. 9-LLAMASCOPE-RES-131K
    11. 99165
    Prev
    Next
    INDEX
    Explanations

    specific domain-related terms or technical jargon

    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
    dens
    -0.07
    é¼
    -0.07
    icone
    -0.07
     Dane
    -0.07
    eness
    -0.06
    ething
    -0.06
     McG
    -0.06
    pliance
    -0.06
    steller
    -0.06
    ovo
    -0.06
    POSITIVE LOGITS
    ÛĮات
    0.07
    oloj
    0.06
     Mixed
    0.06
     Rare
    0.06
     Guam
    0.06
     Carrier
    0.06
     charger
    0.06
    IRA
    0.05
    LING
    0.05
     smoke
    0.05
    Activations Density 0.000%

    No Known Activations