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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96403
    Prev
    Next
    INDEX
    Explanations

    terminology related to economic measurements and financial implications

    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
    622
    -0.06
     mass
    -0.06
    ewe
    -0.06
    ul
    -0.06
     superv
    -0.06
     Mass
    -0.06
    ber
    -0.05
    ode
    -0.05
     weight
    -0.05
    .Interop
    -0.05
    POSITIVE LOGITS
    erosis
    0.08
    ableObject
    0.07
    cles
    0.07
    arris
    0.07
     Lon
    0.07
     sep
    0.07
     addCriterion
    0.07
    velop
    0.07
    ronym
    0.07
    phia
    0.06
    Activations Density 0.002%

    No Known Activations