© 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. 15-LLAMASCOPE-RES-131K
    11. 103352
    Prev
    Next
    INDEX
    Explanations

    expressions of strong positive or negative emotions

    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
    emek
    -0.07
    ãĤıãģij
    -0.07
    دارÛĮ
    -0.06
    chez
    -0.06
     bazen
    -0.06
    åį·
    -0.06
    виг
    -0.06
    ypi
    -0.06
    ehir
    -0.06
    lop
    -0.06
    POSITIVE LOGITS
     indeed
    0.07
    kie
    0.07
    gw
    0.06
    wik
    0.06
    benh
    0.06
    ocado
    0.06
    ohl
    0.06
    orus
    0.06
    ØŃØ©
    0.06
    wald
    0.06
    Activations Density 0.021%

    No Known Activations