© 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. 56294
    Prev
    Next
    INDEX
    Explanations

    complex or abstract concepts often linked to perception or interpretation

    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
     Belgian
    -0.08
    amazon
    -0.08
     Belg
    -0.07
     Ngh
    -0.07
     Moscow
    -0.07
     Duis
    -0.07
     Gh
    -0.07
     amazon
    -0.07
     Albany
    -0.07
     Alger
    -0.07
    POSITIVE LOGITS
     Croatia
    0.10
     Ven
    0.09
    Ven
    0.09
     Naples
    0.08
     Croatian
    0.08
     Venice
    0.08
     Saras
    0.08
     Florida
    0.07
    Florida
    0.07
     Jacksonville
    0.07
    Activations Density 0.041%

    No Known Activations