© 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. 53744
    Prev
    Next
    INDEX
    Explanations

    phrases related to currency and economic conditions

    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
    oe
    -0.07
    wins
    -0.07
    avana
    -0.06
    pow
    -0.06
    itu
    -0.06
    @include
    -0.06
    eps
    -0.06
    279
    -0.06
    876
    -0.06
     Campos
    -0.05
    POSITIVE LOGITS
     currency
    0.08
    rowable
    0.08
    praak
    0.08
    adden
    0.08
     currencies
    0.07
     Exchange
    0.07
     ÑĦÑĥн
    0.07
    ALSE
    0.07
     Currency
    0.07
     Units
    0.07
    Activations Density 0.064%

    No Known Activations