© 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. 91576
    Prev
    Next
    INDEX
    Explanations

    references to financial instruments and trading activities, particularly exchanges and ETFs

    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
    ãĥ©ãĤ¹
    -0.09
    æ¬ł
    -0.06
    arias
    -0.06
    Hit
    -0.06
     Budd
    -0.06
     Brewers
    -0.06
    алÑĮне
    -0.06
    gles
    -0.06
    Bluetooth
    -0.05
    Hp
    -0.05
    POSITIVE LOGITS
    ìĿ´íĦ°
    0.07
     LLP
    0.07
    ceph
    0.06
     Harrison
    0.06
    platform
    0.06
     Labs
    0.06
    -routing
    0.06
     bip
    0.06
     operations
    0.06
    olu
    0.06
    Activations Density 0.010%

    No Known Activations