© 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. 15-LLAMASCOPE-RES-131K
    11. 104151
    Prev
    Next
    INDEX
    Explanations

    specific instances or mentions of notable place names or geographical locations

    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
    sv
    -0.06
    aml
    -0.06
    lica
    -0.06
    æĭ
    -0.06
    orient
    -0.06
    -↵
    -0.06
    ault
    -0.06
    иÑģÑĤÑĢа
    -0.06
    amp
    -0.05
    orable
    -0.05
    POSITIVE LOGITS
    764
    0.07
    forman
    0.07
    PLAIN
    0.07
    uxtap
    0.07
    utow
    0.07
    æĿIJ
    0.07
    classname
    0.07
    762
    0.07
    CTRL
    0.07
     _{}
    0.07
    Activations Density 0.028%

    No Known Activations