© 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. 42627
    Prev
    Next
    INDEX
    Explanations

    references to financial failures and economic crises

    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«ãĥĨ
    -0.07
    strup
    -0.07
    ETO
    -0.07
    alnız
    -0.07
    anvas
    -0.07
    è¦
    -0.07
    _marshall
    -0.07
    HI
    -0.07
    ctal
    -0.07
    CCA
    -0.07
    POSITIVE LOGITS
     overnight
    0.07
    inde
    0.07
     panicked
    0.07
    æĭħ
    0.06
     panic
    0.06
     Tier
    0.06
     Minority
    0.06
    åħ
    0.06
     tier
    0.06
    .stamp
    0.05
    Activations Density 0.023%

    No Known Activations