© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80380
    Prev
    Next
    INDEX
    Explanations

    terms related to financial metrics and economic indicators

    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
    usercontent
    -0.10
    rollo
    -0.08
    .scalablytyped
    -0.08
     dán
    -0.08
    /Peak
    -0.08
    aber
    -0.08
    /loose
    -0.07
    bject
    -0.07
    wil
    -0.07
    endas
    -0.07
    POSITIVE LOGITS
     change
    0.08
     increase
    0.08
     improvement
    0.07
     reduction
    0.07
    change
    0.07
     growth
    0.06
     changes
    0.06
    isse
    0.06
    -in
    0.06
    ince
    0.06
    Activations Density 0.034%

    No Known Activations