© 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. 15920
    Prev
    Next
    INDEX
    Explanations

    references to historical positions or roles held by individuals

    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
    ırı
    -0.08
    .beh
    -0.07
    akis
    -0.07
    μοÏħ
    -0.07
    ìĤ
    -0.06
     Schwar
    -0.06
    prepend
    -0.06
    /document
    -0.06
    alus
    -0.06
    (IService
    -0.06
    POSITIVE LOGITS
    åIJĪ
    0.08
    upal
    0.08
     factory
    0.07
     production
    0.07
     absor
    0.07
     åIJĪ
    0.06
     Factory
    0.06
     Production
    0.06
    Factory
    0.06
     absorbing
    0.06
    Activations Density 0.005%

    No Known Activations