© 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. 26899
    Prev
    Next
    INDEX
    Explanations

    topics related to financial claims and legal matters

    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
    ulp
    -0.07
    marsh
    -0.07
     Estr
    -0.06
    sled
    -0.06
    æŁĦ
    -0.06
    à¥įसर
    -0.06
    attery
    -0.06
     taÅŁ
    -0.06
    izia
    -0.06
    kovi
    -0.06
    POSITIVE LOGITS
    quo
    0.07
     recognition
    0.07
     inclusion
    0.06
    än
    0.06
    igh
    0.06
    ComputedStyle
    0.06
    ·»
    0.06
    ssue
    0.06
     Shares
    0.06
    ade
    0.05
    Activations Density 0.032%

    No Known Activations