© 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. 79032
    Prev
    Next
    INDEX
    Explanations

    adjectives describing emotional states or qualities of experiences

    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
    /ay
    -0.07
    uzzi
    -0.07
    oro
    -0.07
    Ｉ
    -0.07
    ando
    -0.07
    ROUGH
    -0.07
    \Migrations
    -0.07
    variant
    -0.06
    леÑĩ
    -0.06
    logfile
    -0.06
    POSITIVE LOGITS
     affair
    0.12
     phenomenon
    0.11
     phenomena
    0.10
     thing
    0.10
     matter
    0.09
     Thing
    0.08
     entity
    0.07
     affairs
    0.07
     cosa
    0.07
    thing
    0.07
    Activations Density 0.049%

    No Known Activations