© 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. 16022
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and sentiments related to love and well-wishing

    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
    uli
    -0.07
    ohl
    -0.07
    ony
    -0.07
    onus
    -0.07
    antar
    -0.07
    allen
    -0.07
    ä¹İ
    -0.06
    ianne
    -0.06
    ComputedStyle
    -0.06
    als
    -0.06
    POSITIVE LOGITS
    eref
    0.07
    ÏĥÏĩ
    0.06
    osen
    0.06
    Ư
    0.06
     today
    0.05
    yna
    0.05
    acus
    0.05
    ãĥĭãĤ¢
    0.05
    SHARE
    0.05
    reshold
    0.05
    Activations Density 0.002%

    No Known Activations