© 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. 56525
    Prev
    Next
    INDEX
    Explanations

    references to historical conflict and colonial dynamics

    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
    chemy
    -0.08
    hetto
    -0.07
    chner
    -0.07
    euillez
    -0.07
    aggio
    -0.07
    esen
    -0.07
    utsch
    -0.07
    FFFFFFFF
    -0.07
    767
    -0.07
     dna
    -0.06
    POSITIVE LOGITS
     Russians
    0.09
     Romans
    0.09
     Americans
    0.09
     Greeks
    0.08
     Koreans
    0.08
     Germans
    0.07
     Europeans
    0.07
     Israelis
    0.07
     Indians
    0.07
     Australians
    0.07
    Activations Density 0.115%

    No Known Activations