© 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. 126355
    Prev
    Next
    INDEX
    Explanations

    themes of respect and hierarchical relationships, particularly regarding elders

    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
    ampion
    -0.07
     Sisters
    -0.07
    pend
    -0.07
    иÑĤов
    -0.07
    znik
    -0.07
    omu
    -0.07
    inç
    -0.07
    orgot
    -0.06
    eree
    -0.06
    .community
    -0.06
    POSITIVE LOGITS
     defer
    0.13
     respect
    0.11
     elder
    0.09
    respect
    0.09
     Respect
    0.09
     authority
    0.09
    defer
    0.09
     seniors
    0.08
     senior
    0.08
    å°Ĭ
    0.08
    Activations Density 0.062%

    No Known Activations