© 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. 103398
    Prev
    Next
    INDEX
    Explanations

    phrases indicating good fortune or positive 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
    acr
    -0.06
    voy
    -0.06
    /topics
    -0.06
    geme
    -0.06
    EM
    -0.06
    crawl
    -0.06
    tec
    -0.06
     vacc
    -0.06
    ubit
    -0.06
    ln
    -0.05
    POSITIVE LOGITS
    iale
    0.08
     rare
    0.07
     Rare
    0.07
    odo
    0.07
    acha
    0.07
    Rare
    0.07
     lucky
    0.07
     fortunate
    0.06
     Burl
    0.06
     Spot
    0.06
    Activations Density 0.010%

    No Known Activations