© 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. 125515
    Prev
    Next
    INDEX
    Explanations

    concepts related to financial advising and ethical standards

    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
    brig
    -0.08
    izzo
    -0.08
    bud
    -0.07
     Strom
    -0.07
    eba
    -0.07
    orra
    -0.07
    Touches
    -0.07
    оÑĢоÑĤ
    -0.06
    POOL
    -0.06
     شد
    -0.06
    POSITIVE LOGITS
     interests
    0.13
     welfare
    0.10
     concerns
    0.10
    åĪ©
    0.08
     Welfare
    0.08
     priorities
    0.08
     concern
    0.08
     conflicts
    0.08
     priority
    0.08
     serving
    0.07
    Activations Density 0.134%

    No Known Activations