© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117160
    Prev
    Next
    INDEX
    Explanations

    instances of ironic or sarcastic commentary

    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
    UrlParser
    -0.10
    RuntimeObject
    -0.09
    //**↵
    -0.09
    HeaderCode
    -0.08
    GuidId
    -0.08
    URLException
    -0.08
    /Dk
    -0.08
    yonel
    -0.08
    imas
    -0.08
    Äįas
    -0.08
    POSITIVE LOGITS
    0.08
     ones
    0.07
     if
    0.06
     it
    0.06
    it
    0.06
    l
    0.06
     Window
    0.06
    0
    0.06
     dong
    0.06
     they
    0.05
    Activations Density 0.000%

    No Known Activations