© 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. 123277
    Prev
    Next
    INDEX
    Explanations

    words related to professional skills and attributes

    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
    alar
    -0.06
     civilian
    -0.06
     Wage
    -0.05
    ope
    -0.05
    ija
    -0.05
     microtime
    -0.05
    awan
    -0.05
     intents
    -0.05
    ufen
    -0.05
     Andres
    -0.05
    POSITIVE LOGITS
     Clients
    0.07
    Clients
    0.07
    iyim
    0.07
    uhan
    0.07
     clients
    0.07
     insp
    0.07
     RESULTS
    0.07
    odal
    0.07
    ìĥģìľĦ
    0.07
     CLIENT
    0.07
    Activations Density 0.045%

    No Known Activations