© 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. 22-LLAMASCOPE-RES-131K
    11. 3643
    Prev
    Next
    INDEX
    Explanations

    definite articles and their variation in different contexts

    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
    oret
    -0.07
    iste
    -0.07
    rem
    -0.07
    iem
    -0.06
    her
    -0.06
    tr
    -0.06
    amin
    -0.06
    uk
    -0.06
    sim
    -0.06
    chie
    -0.06
    POSITIVE LOGITS
    nyder
    0.07
    baugh
    0.07
    icism
    0.06
    esseract
    0.06
    etable
    0.06
    olson
    0.06
    eken
    0.06
    ammer
    0.06
    ounty
    0.06
    agens
    0.06
    Activations Density 0.020%

    No Known Activations