© 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. 119047
    Prev
    Next
    INDEX
    Explanations

    sequences of letters and sounds that suggest excitement or emphasis

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

    Greetings, farewells, or cultural expressions in various languages that serve as interjections or social acknowledgments in text.

    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
    _pins
    -0.06
    ardo
    -0.06
    ãĤĵãģ©
    -0.06
     haus
    -0.06
    imei
    -0.06
    ãģıãģ®
    -0.06
    onte
    -0.06
    ayla
    -0.06
    lab
    -0.06
     tarafından
    -0.06
    POSITIVE LOGITS
     indeed
    0.08
    !
    0.07
    orus
    0.06
    urret
    0.06
    ale
    0.06
    áze
    0.06
    ãģ¾ãģĽ
    0.06
    reater
    0.06
    ABCDEFGHIJKLMNOP
    0.06
     America
    0.06
    Activations Density 0.030%

    No Known Activations