© 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. 71600
    Prev
    Next
    INDEX
    Explanations

    references to corruption scandals and their impacts on governance

    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
     España
    -0.07
    Spain
    -0.07
     español
    -0.07
     GarcÃŃa
    -0.07
     puerto
    -0.06
    Hola
    -0.06
     Spain
    -0.06
     ÐĺÑģп
    -0.06
    lect
    -0.06
     Gibraltar
    -0.06
    POSITIVE LOGITS
     Brazilian
    0.19
     Brazil
    0.17
    Brazil
    0.16
     Brasil
    0.15
     brazil
    0.14
     brasile
    0.14
     São
    0.12
     Braz
    0.11
     Bras
    0.11
    ôn
    0.10
    Activations Density 0.162%

    No Known Activations