© 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. 88059
    Prev
    Next
    INDEX
    Explanations

    instances of the word "like" used as a discourse marker

    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
    ãĥ¬ãĥĥãĥĪ
    -0.08
    AGMA
    -0.08
    емон
    -0.07
    ç¯Ģ
    -0.07
     gezocht
    -0.07
     lẫn
    -0.07
    Ãły
    -0.07
    lio
    -0.07
    emoc
    -0.07
    ImageContext
    -0.07
    POSITIVE LOGITS
    :↵
    0.06
    aviest
    0.06
    :
    0.06
    -minded
    0.06
     t
    0.06
     nam
    0.06
     g
    0.05
    ,
    0.05
     c
    0.05
     nature
    0.05
    Activations Density 0.006%

    No Known Activations