© 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. 17-LLAMASCOPE-RES-131K
    11. 3115
    Prev
    Next
    INDEX
    Explanations

    concepts related to social or communal frameworks and their interactions

    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
    canf
    -0.07
    üz
    -0.07
    _dispatcher
    -0.07
     kolej
    -0.07
     DISPATCH
    -0.07
    )(__
    -0.07
     hete
    -0.07
    ongyang
    -0.07
    .AppSettings
    -0.07
     destinationViewController
    -0.07
    POSITIVE LOGITS
    /or
    0.10
    aine
    0.06
    ones
    0.06
    rawn
    0.06
     rather
    0.06
    ernal
    0.06
    sville
    0.06
     nonlinear
    0.06
    ä¸Ķ
    0.06
     organ
    0.06
    Activations Density 0.041%

    No Known Activations