© 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. 62935
    Prev
    Next
    INDEX
    Explanations

    references to company decisions affecting employment and operations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     backing
    -0.07
    usercontent
    -0.07
    átka
    -0.07
     nackte
    -0.06
    upported
    -0.06
    asurer
    -0.06
    زب
    -0.06
     Stateless
    -0.06
    ftware
    -0.06
    .nano
    -0.06
    POSITIVE LOGITS
     employee
    0.09
     Employee
    0.08
     employees
    0.08
     job
    0.07
     company
    0.07
    ioni
    0.07
    indow
    0.06
     WARN
    0.06
     Company
    0.06
     Employees
    0.06
    Activations Density 0.008%

    No Known Activations