© 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 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. 118674
    Prev
    Next
    INDEX
    Explanations

    elementos relacionados con la infraestructura y la capacidad operativa de una empresa

    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
    udur
    -0.07
    dney
    -0.07
    PLUGIN
    -0.07
    gere
    -0.07
     Observatory
    -0.07
    ozor
    -0.07
    _exports
    -0.07
    Maker
    -0.07
     putas
    -0.06
     unzip
    -0.06
    POSITIVE LOGITS
     region
    0.07
     Ac
    0.07
    -service
    0.07
     service
    0.07
     divisions
    0.06
    Regs
    0.06
     leaders
    0.06
     Service
    0.06
     acquired
    0.06
     acute
    0.06
    Activations Density 0.049%

    No Known Activations