© 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. 90132
    Prev
    Next
    INDEX
    Explanations

    references to legal and accountability issues related to veterans' affairs

    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
     Pediatric
    -0.06
    ullo
    -0.06
    ete
    -0.06
    nar
    -0.06
    é³´
    -0.06
    .NET
    -0.06
     copp
    -0.06
    ubes
    -0.06
    μÏĨ
    -0.06
    lio
    -0.05
    POSITIVE LOGITS
     VA
    0.09
     service
    0.08
    .va
    0.08
    service
    0.08
     Service
    0.08
    -service
    0.08
    ervice
    0.07
    pons
    0.07
    ÑĸнÑĮ
    0.07
    owa
    0.07
    Activations Density 0.017%

    No Known Activations