© 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. 27545
    Prev
    Next
    INDEX
    Explanations

    references to demographic and economic statistics

    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
    oud
    -0.07
    itemap
    -0.06
     mil
    -0.06
    aras
    -0.06
    ash
    -0.06
    arend
    -0.06
    otu
    -0.06
    amon
    -0.06
     kostenlose
    -0.06
    eya
    -0.06
    POSITIVE LOGITS
     buying
    0.10
     purchasing
    0.10
     consumer
    0.10
     Buying
    0.10
    consumer
    0.09
     Consumer
    0.09
    _consumer
    0.09
     spending
    0.08
    _TestCase
    0.08
    -buy
    0.08
    Activations Density 0.009%

    No Known Activations