© 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. 39383
    Prev
    Next
    INDEX
    Explanations

    quantitative data and metrics related to business and organizational structures

    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
    alat
    -0.07
     Telecom
    -0.07
    ibur
    -0.07
     Boiler
    -0.07
    Tenant
    -0.06
     cort
    -0.06
    åĿĬ
    -0.06
    ansom
    -0.06
    Gate
    -0.06
     Gate
    -0.06
    POSITIVE LOGITS
     dealer
    0.10
     Dealers
    0.09
     Dealer
    0.09
     car
    0.09
     dealership
    0.09
     dealers
    0.09
    Dealer
    0.09
     vehicle
    0.07
    dealer
    0.07
    otos
    0.07
    Activations Density 0.022%

    No Known Activations