© 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. 61370
    Prev
    Next
    INDEX
    Explanations

    negative qualifiers and their usage in a statement

    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
    isque
    -0.07
    .GetById
    -0.07
    /↵↵↵↵
    -0.06
    ovol
    -0.06
     Lev
    -0.06
    xce
    -0.06
    isol
    -0.06
    yen
    -0.06
     ple
    -0.06
     elé
    -0.06
    POSITIVE LOGITS
    aura
    0.07
    urre
    0.07
     servisi
    0.06
     æ°¸
    0.06
    _esc
    0.06
    uel
    0.06
    irma
    0.06
    ospace
    0.06
    uyor
    0.06
    ÛĮÙģ
    0.06
    Activations Density 0.001%

    No Known Activations