© 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. 26916
    Prev
    Next
    INDEX
    Explanations

    phrases related to responsibility and obligation

    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
    uffle
    -0.07
    agi
    -0.07
     laure
    -0.07
    Ĺi
    -0.07
    aint
    -0.06
    gh
    -0.06
    swers
    -0.06
    coli
    -0.06
    ney
    -0.06
    reh
    -0.06
    POSITIVE LOGITS
     McCart
    0.07
     ÑĢаб
    0.07
     cả
    0.06
    æĪIJç«ĭ
    0.06
     ÃŃch
    0.06
    اÙĨÚ¯
    0.06
     alternatively
    0.06
     ^{°}
    0.06
     basket
    0.06
    annt
    0.06
    Activations Density 0.000%

    No Known Activations