© 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. 95809
    Prev
    Next
    INDEX
    Explanations

    references to job growth and economic performance metrics

    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
    olith
    -0.07
    locker
    -0.07
    emento
    -0.07
     localVar
    -0.06
     Eternal
    -0.06
    LOB
    -0.06
    otti
    -0.06
    afa
    -0.06
    //{{
    -0.06
    andom
    -0.06
    POSITIVE LOGITS
     periods
    0.08
    _periods
    0.07
    Fed
    0.07
     period
    0.07
    ADOW
    0.06
    period
    0.06
    enk
    0.06
    .period
    0.06
     Fed
    0.06
    $key
    0.06
    Activations Density 0.005%

    No Known Activations