© 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. 15-LLAMASCOPE-RES-131K
    11. 88320
    Prev
    Next
    INDEX
    Explanations

    concepts related to separation and differentiation

    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
    477
    -0.09
    uai
    -0.08
    ToDevice
    -0.07
    704
    -0.07
    pga
    -0.07
    422
    -0.07
    лÑİ
    -0.07
    itmap
    -0.06
    ooth
    -0.06
    /sidebar
    -0.06
    POSITIVE LOGITS
     khá»ıi
    0.09
     apart
    0.08
     Hava
    0.07
     among
    0.07
     Shar
    0.07
    istingu
    0.06
    ongyang
    0.06
    forge
    0.06
    mere
    0.06
    istinguish
    0.06
    Activations Density 0.025%

    No Known Activations