© 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. 17-LLAMASCOPE-RES-131K
    11. 4392
    Prev
    Next
    INDEX
    Explanations

    phrases related to promotional offers or sales

    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
    uga
    -0.07
    ÑĢоÑĪ
    -0.07
    egasus
    -0.06
    icion
    -0.06
    ãģ¡ãĤĥ
    -0.06
    ua
    -0.06
    ot
    -0.05
    inton
    -0.05
    ettel
    -0.05
     Crud
    -0.05
    POSITIVE LOGITS
     Clearance
    0.07
     clearance
    0.07
    ordova
    0.07
     Stocks
    0.07
    raphics
    0.07
    stown
    0.07
     stocks
    0.06
     Canter
    0.06
    943
    0.06
     \/
    0.06
    Activations Density 0.000%

    No Known Activations