© 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. 15-LLAMASCOPE-RES-131K
    11. 86897
    Prev
    Next
    INDEX
    Explanations

    discussions related to economic and social issues

    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
    elan
    -0.07
    asher
    -0.07
     Tactics
    -0.06
    ennie
    -0.06
    ansa
    -0.06
    esz
    -0.06
    zac
    -0.06
    iego
    -0.06
    razil
    -0.06
    ieres
    -0.06
    POSITIVE LOGITS
     Burl
    0.08
    Ownership
    0.07
    chs
    0.07
     McCart
    0.07
    -transitional
    0.07
    qml
    0.06
    ابÙĩ
    0.06
    ÑħÑĸд
    0.06
    -----------*/↵
    0.06
    Wunused
    0.06
    Activations Density 0.001%

    No Known Activations