© 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. 16216
    Prev
    Next
    INDEX
    Explanations

    information about organic products and their availability

    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
    ugu
    -0.07
    rego
    -0.07
    .ObjectModel
    -0.06
     Millenn
    -0.06
     Doll
    -0.06
     vidé
    -0.06
     disag
    -0.06
     Rae
    -0.06
    ernel
    -0.06
    ÑĢаг
    -0.06
    POSITIVE LOGITS
     yeast
    0.10
     brewery
    0.09
    beer
    0.09
     beer
    0.09
     breweries
    0.09
     beers
    0.09
     Brewery
    0.08
     hops
    0.08
    Beer
    0.07
     Brewing
    0.07
    Activations Density 0.044%

    No Known Activations