© 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. 84128
    Prev
    Next
    INDEX
    Explanations

    phrases related to product performance and features

    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
    ascar
    -0.07
    afx
    -0.07
     اÙĦرÙħزÙĬØ©
    -0.07
     sparing
    -0.07
    essional
    -0.07
     vitam
    -0.07
     :↵↵↵↵
    -0.07
    iphone
    -0.07
    ocab
    -0.07
    agara
    -0.07
    POSITIVE LOGITS
     price
    0.06
    nek
    0.06
     Core
    0.06
    sz
    0.06
     performance
    0.06
     value
    0.06
     competitive
    0.06
    PEG
    0.06
    itz
    0.06
     perform
    0.06
    Activations Density 0.003%

    No Known Activations