© 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. 94026
    Prev
    Next
    INDEX
    Explanations

    frequent usage of the word "the," indicating a focus on common or generic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The definite article "the" appearing in promotional or informational website content, often before nouns referring to products, services, programs or content that the website wants users to engage with.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    mares
    -0.07
    .createClass
    -0.07
     Syndrome
    -0.07
    atura
    -0.07
    idine
    -0.07
    ALLED
    -0.07
    fel
    -0.06
    .mybatis
    -0.06
    existence
    -0.06
     existence
    -0.06
    POSITIVE LOGITS
     your
    0.07
    avl
    0.06
    786
    0.06
     flatt
    0.06
    ssp
    0.06
    'gc
    0.06
     #
    0.06
    olit
    0.06
     wherever
    0.06
    oran
    0.06
    Activations Density 0.048%

    No Known Activations