© 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. 5783
    Prev
    Next
    INDEX
    Explanations

    topics related to financial challenges and unforeseen life events

    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
    omy
    -0.07
    etto
    -0.06
    resh
    -0.06
    åį±
    -0.06
     carrier
    -0.06
     field
    -0.06
     Cas
    -0.06
    ritel
    -0.06
    ắng
    -0.06
    thers
    -0.06
    POSITIVE LOGITS
     unexpectedly
    0.09
     unexpected
    0.08
     sudden
    0.08
    unexpected
    0.08
     medical
    0.08
     suddenly
    0.07
     illness
    0.07
    inton
    0.07
     Unexpected
    0.07
    rain
    0.07
    Activations Density 0.006%

    No Known Activations