© 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. 85184
    Prev
    Next
    INDEX
    Explanations

    specific geographical and historical references within a cultural context

    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
     mountain
    -0.08
     Mountain
    -0.08
    Mountain
    -0.08
     Austrian
    -0.07
     Alpine
    -0.07
     cave
    -0.07
     Colorado
    -0.07
     Birmingham
    -0.06
     canyon
    -0.06
     Cave
    -0.06
    POSITIVE LOGITS
     Baltic
    0.11
     Estonia
    0.10
     Lithuania
    0.09
     Eston
    0.09
     Lutheran
    0.08
     Latvia
    0.08
     Finland
    0.08
    utow
    0.07
     Helsinki
    0.07
     Manitoba
    0.07
    Activations Density 0.056%

    No Known Activations