© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76182
    Prev
    Next
    INDEX
    Explanations

    positive expressions related to enjoyment and appreciation 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
    YW
    -0.07
    etri
    -0.07
    okie
    -0.07
    oux
    -0.06
    /Documents
    -0.06
     dom
    -0.06
    utherland
    -0.06
     Zuk
    -0.06
    باز
    -0.06
    ched
    -0.06
    POSITIVE LOGITS
     life
    0.07
     moment
    0.06
    lijk
    0.06
     sir
    0.06
    ably
    0.06
    öl
    0.06
     ÙħÙĤدÙħ
    0.06
    ubi
    0.06
    entine
    0.06
    abwe
    0.06
    Activations Density 0.012%

    No Known Activations