© 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. 79112
    Prev
    Next
    INDEX
    Explanations

    emotional responses and expressions related to people and their situations

    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
    rame
    -0.07
    _tolerance
    -0.07
    INDER
    -0.07
    лиÑĪ
    -0.06
    upe
    -0.06
    anto
    -0.06
    âĢª
    -0.06
    icho
    -0.06
    vale
    -0.06
    uC
    -0.06
    POSITIVE LOGITS
    582
    0.07
     forgot
    0.07
    sei
    0.07
     Forgot
    0.07
    itz
    0.06
    338
    0.06
     Dove
    0.06
    GRE
    0.06
    ui
    0.06
    Gui
    0.06
    Activations Density 0.015%

    No Known Activations