© 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 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. 57369
    Prev
    Next
    INDEX
    Explanations

    emotions and their expressions in dialogue

    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
    Äįi
    -0.07
    antar
    -0.07
     naken
    -0.07
    dzi
    -0.07
    ija
    -0.06
    izo
    -0.06
     Kemp
    -0.06
    .MixedReality
    -0.06
    467
    -0.06
    ssi
    -0.06
    POSITIVE LOGITS
    ½
    0.07
    ques
    0.06
    /latest
    0.06
    urance
    0.06
    -looking
    0.06
    haar
    0.06
    ãĥ³ãĥIJãĥ¼
    0.06
    ofire
    0.06
    while
    0.06
    ness
    0.06
    Activations Density 0.021%

    No Known Activations