© 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. 121293
    Prev
    Next
    INDEX
    Explanations

    financial data related to mortgage delinquencies and foreclosures

    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
    jak
    -0.07
     Bounty
    -0.07
     dán
    -0.07
    icus
    -0.06
    etto
    -0.06
     Playboy
    -0.06
    .mozilla
    -0.06
    ë²
    -0.06
    iid
    -0.06
    SSERT
    -0.06
    POSITIVE LOGITS
    ungs
    0.07
    lo
    0.07
     bad
    0.07
     sol
    0.06
    ifa
    0.06
    bad
    0.06
     Nec
    0.06
    hips
    0.06
    akes
    0.06
     Wells
    0.06
    Activations Density 0.019%

    No Known Activations