© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15888
    Prev
    Next
    INDEX
    Explanations

    references to political events and international relations

    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
    ernaut
    -0.06
     teh
    -0.06
    arus
    -0.06
    arrera
    -0.06
    uries
    -0.06
    alim
    -0.06
    ethod
    -0.06
    atu
    -0.05
    ailable
    -0.05
    umer
    -0.05
    POSITIVE LOGITS
    992
    0.07
     bdsm
    0.07
    oola
    0.07
    }elseif
    0.07
     defaultMessage
    0.07
    ãģĸ
    0.06
    cad
    0.06
     agenda
    0.06
    ļĮ
    0.06
     itinerary
    0.06
    Activations Density 0.008%

    No Known Activations