© 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. 15-LLAMASCOPE-RES-131K
    11. 27245
    Prev
    Next
    INDEX
    Explanations

    phrases related to commitments and obligations

    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
    aring
    -0.07
    ekim
    -0.06
    inox
    -0.06
    lib
    -0.06
    widgets
    -0.06
    äº
    -0.06
    strained
    -0.06
    335
    -0.06
     bgcolor
    -0.06
    allet
    -0.06
    POSITIVE LOGITS
    Spo
    0.07
     Spo
    0.07
    evi
    0.06
     Spoon
    0.06
    žel
    0.06
    .sul
    0.06
    uft
    0.06
     spoil
    0.06
    æ¢
    0.06
     Loot
    0.06
    Activations Density 0.001%

    No Known Activations