© 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. 89054
    Prev
    Next
    INDEX
    Explanations

    references to organizational structure and relationships within a community

    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
    awl
    -0.06
    :↵
    -0.06
     jednak
    -0.06
     pÅĻiÄįemž
    -0.06
    letter
    -0.06
    ÅĻ
    -0.06
     Than
    -0.06
    è
    -0.06
    }elseif
    -0.06
     detriment
    -0.06
    POSITIVE LOGITS
    /or
    0.10
    ients
    0.09
     alike
    0.09
    uxtap
    0.09
     subsequent
    0.08
     accompanying
    0.08
    reas
    0.07
    entai
    0.07
    rog
    0.07
     associated
    0.07
    Activations Density 0.089%

    No Known Activations