© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126022
    Prev
    Next
    INDEX
    Explanations

    references to locations and events related to art exhibitions and significant cultural subjects

    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
    ipel
    -0.07
     Portuguese
    -0.06
    borg
    -0.06
    941
    -0.06
     kola
    -0.06
    ouro
    -0.06
     counties
    -0.06
     stap
    -0.06
     Nunes
    -0.06
     pik
    -0.06
    POSITIVE LOGITS
     Mexico
    0.13
     México
    0.12
     Mexican
    0.11
    Mexico
    0.11
    ahu
    0.11
    .mx
    0.11
     MX
    0.10
    ihu
    0.10
    MX
    0.10
     mex
    0.09
    Activations Density 0.191%

    No Known Activations