© 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. 75304
    Prev
    Next
    INDEX
    Explanations

    references to alternate realities or dystopian settings

    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
    740
    -0.08
    анÑģи
    -0.08
    jang
    -0.08
    æ¶
    -0.07
    zens
    -0.07
     ÙħشاÙĩ
    -0.07
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.07
    _RCC
    -0.07
    aina
    -0.07
    ichick
    -0.07
    POSITIVE LOGITS
     Gone
    0.07
    úa
    0.06
     society
    0.06
     Leisure
    0.06
     Earth
    0.06
     gone
    0.06
     Chin
    0.06
     leisure
    0.06
     government
    0.06
     corporations
    0.06
    Activations Density 0.034%

    No Known Activations