© 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. 5876
    Prev
    Next
    INDEX
    Explanations

    terms related to changes and stability in financial or economic contexts

    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
    _NC
    -0.08
    linkplain
    -0.08
    loat
    -0.07
    owe
    -0.07
    owski
    -0.06
    akes
    -0.06
    abis
    -0.06
     abych
    -0.06
    ragen
    -0.06
     Belle
    -0.06
    POSITIVE LOGITS
    ifest
    0.08
     of
    0.07
    zÄħd
    0.06
     regarding
    0.06
    unft
    0.06
    quals
    0.06
    ocal
    0.06
    chants
    0.06
    ãĥ¼ãĥ³
    0.06
    inus
    0.06
    Activations Density 0.070%

    No Known Activations