© 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. 22-LLAMASCOPE-RES-131K
    11. 4120
    Prev
    Next
    INDEX
    Explanations

    terms related to arts, culture, and the creative industry

    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
    ÑĢава
    -0.08
    issen
    -0.08
    nej
    -0.07
     attacker
    -0.07
    lesc
    -0.07
    ollower
    -0.07
     newcomer
    -0.07
    uren
    -0.07
     stranger
    -0.07
    ÑıÑĤелÑĮ
    -0.07
    POSITIVE LOGITS
     experts
    0.10
     specialists
    0.10
     professionals
    0.09
     strateg
    0.09
     folk
    0.08
     specialist
    0.08
     workers
    0.08
    profession
    0.08
     evalu
    0.08
     expert
    0.07
    Activations Density 0.072%

    No Known Activations