© 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. 17-LLAMASCOPE-RES-131K
    11. 3152
    Prev
    Next
    INDEX
    Explanations

    terms related to machinery manufacturing and supply

    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
    idian
    -0.07
    chip
    -0.06
    gem
    -0.06
    RIPT
    -0.06
    ucas
    -0.06
    ONY
    -0.06
    .epam
    -0.06
    iasi
    -0.06
    elan
    -0.06
     Outline
    -0.06
    POSITIVE LOGITS
    anst
    0.07
     Hast
    0.06
    ANCE
    0.06
     Shim
    0.06
     ISO
    0.06
    оÑĢоÑĤ
    0.06
    ammo
    0.06
     shipments
    0.06
     bulk
    0.06
     shipment
    0.06
    Activations Density 0.000%

    No Known Activations