© 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. 15-LLAMASCOPE-RES-131K
    11. 88891
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to future plans and developments in the tech industry

    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
    arrera
    -0.07
    teki
    -0.07
    shal
    -0.07
    kte
    -0.06
    ston
    -0.06
    NCY
    -0.06
    enin
    -0.06
    oucher
    -0.06
    eneg
    -0.06
    bih
    -0.06
    POSITIVE LOGITS
    azor
    0.08
    twig
    0.06
     strategy
    0.06
     plan
    0.06
     Strategy
    0.06
    .Gen
    0.06
     targets
    0.06
     Plan
    0.06
     eccentric
    0.06
     lately
    0.06
    Activations Density 0.008%

    No Known Activations