© 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 EvalsExportsinterp-engineNEWAPI 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. 124799
    Prev
    Next
    INDEX
    Explanations

    words indicating connections or relationships among entities

    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
    oly
    -0.07
    elez
    -0.07
    á»įt
    -0.07
     ÙĪاÙĦÙĨ
    -0.07
    cep
    -0.06
    usi
    -0.06
    urger
    -0.06
    ute
    -0.06
    zept
    -0.06
     Geographic
    -0.06
    POSITIVE LOGITS
     abroad
    0.10
     elsewhere
    0.10
     worldwide
    0.09
     global
    0.09
    global
    0.08
     other
    0.08
     world
    0.08
     beyond
    0.08
    Else
    0.08
     Europe
    0.07
    Activations Density 0.024%

    No Known Activations