© 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. 70201
    Prev
    Next
    INDEX
    Explanations

    sentiments of sarcasm and insincerity

    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
     nackte
    -0.08
    iffany
    -0.07
    ÃŃÅĻ
    -0.07
    odable
    -0.07
    imetype
    -0.06
    enment
    -0.06
     billig
    -0.06
    anggal
    -0.06
    елÑİ
    -0.06
    aviour
    -0.06
    POSITIVE LOGITS
     sorry
    0.13
     Sorry
    0.12
    Sorry
    0.11
    sorry
    0.11
     disappointment
    0.07
     disappointed
    0.07
     disappointing
    0.07
     Tough
    0.06
    onz
    0.06
    try
    0.06
    Activations Density 0.047%

    No Known Activations