© 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. 9-LLAMASCOPE-RES-131K
    11. 95757
    Prev
    Next
    INDEX
    Explanations

    emotional and sensory experiences related to winning and enjoyment

    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
    isma
    -0.07
    /loader
    -0.07
    Å¡il
    -0.07
    usz
    -0.06
    ãĥ¼ãĥį
    -0.06
    empl
    -0.06
    ë¡Ŀ
    -0.06
    emplates
    -0.06
    yah
    -0.06
    adem
    -0.06
    POSITIVE LOGITS
    ubyte
    0.06
     комÑĥ
    0.06
     reserved
    0.06
    ruk
    0.06
    atern
    0.06
    ئة
    0.06
     reserves
    0.06
    icont
    0.06
     least
    0.06
    odont
    0.06
    Activations Density 0.022%

    No Known Activations