© 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. 626
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of reality, particularly in relation to honesty, truthfulness, and authenticity

    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
    oogle
    -0.07
    ÅĦ
    -0.06
    eling
    -0.06
    okane
    -0.06
    USR
    -0.06
     componentWillMount
    -0.06
    лоÑĢ
    -0.06
    ç±į
    -0.06
    coni
    -0.06
    ÙĪÙĤÙģ
    -0.06
    POSITIVE LOGITS
    /false
    0.09
     truly
    0.07
     McCoy
    0.07
    ationship
    0.07
    st
    0.07
     Truly
    0.07
     underlying
    0.07
    Behind
    0.07
    aurant
    0.07
    igned
    0.06
    Activations Density 0.010%

    No Known Activations