© 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. 1371
    Prev
    Next
    INDEX
    Explanations

    financial growth and investment accumulation concepts

    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
     Consort
    -0.06
    endum
    -0.06
     budgets
    -0.06
    ensed
    -0.06
    entine
    -0.06
    ardy
    -0.05
    ipel
    -0.05
    è´¨
    -0.05
    845
    -0.05
    ientes
    -0.05
    POSITIVE LOGITS
    .asset
    0.08
    growth
    0.07
    asset
    0.07
     investment
    0.07
    investment
    0.07
     asset
    0.06
     rein
    0.06
    надлеж
    0.06
    ezi
    0.06
    idia
    0.06
    Activations Density 0.010%

    No Known Activations