© 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. 69247
    Prev
    Next
    INDEX
    Explanations

    terms related to bankruptcy and its associated costs

    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
    MainFrame
    -0.08
    .scalablytyped
    -0.08
    ULL
    -0.07
    еÑĢж
    -0.07
    esome
    -0.07
    ono
    -0.07
    aidu
    -0.07
    857
    -0.07
    WRAPPER
    -0.07
    álo
    -0.07
    POSITIVE LOGITS
    mony
    0.06
     Indexed
    0.06
     Dep
    0.06
    inp
    0.06
    ashtra
    0.06
     pé
    0.06
    _GRE
    0.06
     MVP
    0.06
    itus
    0.05
    emann
    0.05
    Activations Density 0.002%

    No Known Activations