© 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. 3530
    Prev
    Next
    INDEX
    Explanations

    elements related to organizational structure and operational capabilities

    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
     might
    -0.07
     none
    -0.06
     do
    -0.06
    목
    -0.06
     other
    -0.06
    mlin
    -0.06
     would
    -0.05
     al
    -0.05
     unlikely
    -0.05
    aram
    -0.05
    POSITIVE LOGITS
     noi
    0.08
    edith
    0.08
     naše
    0.08
     nosotros
    0.08
     наÑĪей
    0.08
     naÅ¡ÃŃ
    0.08
     chúng
    0.07
     kami
    0.07
     nostro
    0.07
    'gc
    0.07
    Activations Density 0.019%

    No Known Activations