© 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. 29534
    Prev
    Next
    INDEX
    Explanations

    references to violations of laws or rules

    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
    .scalablytyped
    -0.09
    λι
    -0.09
    utory
    -0.08
    arde
    -0.08
    onde
    -0.08
    æŀĿ
    -0.07
    onga
    -0.07
    czy
    -0.07
    .initializeApp
    -0.07
    ellite
    -0.07
    POSITIVE LOGITS
     rules
    0.11
     laws
    0.10
     norms
    0.09
     orders
    0.08
     by
    0.08
     principles
    0.07
     regulations
    0.07
    rules
    0.07
     expectations
    0.07
     bounds
    0.07
    Activations Density 0.020%

    No Known Activations