© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39130
    Prev
    Next
    INDEX
    Explanations

    references to individuals' career accomplishments and professional backgrounds

    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
    educated
    -0.09
    University
    -0.08
     college
    -0.08
     University
    -0.08
     graduating
    -0.08
     university
    -0.08
    -educated
    -0.08
     Universities
    -0.08
     оÑģвÑĸ
    -0.08
    education
    -0.08
    POSITIVE LOGITS
    oor
    0.06
    ิà¸ĩ
    0.06
    hic
    0.06
    ÑĨез
    0.06
    ì°®
    0.06
     sach
    0.06
    ibur
    0.06
    ocker
    0.05
    oby
    0.05
    atables
    0.05
    Activations Density 0.036%

    No Known Activations