© 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. 15-LLAMASCOPE-RES-131K
    11. 86222
    Prev
    Next
    INDEX
    Explanations

    instances of phrases that suggest financial transactions or payments

    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
    ollower
    -0.07
     ÙĤص
    -0.06
    kits
    -0.06
     hrom
    -0.06
    293
    -0.06
    åħ´
    -0.06
    ιÏĥÏĦή
    -0.06
    licer
    -0.06
    jte
    -0.06
     Intervention
    -0.05
    POSITIVE LOGITS
    antro
    0.07
    abbo
    0.07
    мÑı
    0.07
    úc
    0.07
    odash
    0.07
    aci
    0.06
    agma
    0.06
    egl
    0.06
    ohan
    0.06
     cancer
    0.06
    Activations Density 0.000%

    No Known Activations