© 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. 4245
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to moral values and ethical behavior

    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
    ional
    -0.07
    iated
    -0.07
     Gos
    -0.06
     switch
    -0.06
    cher
    -0.06
    iate
    -0.06
     Fur
    -0.06
    ÑĥÑĢг
    -0.06
    ario
    -0.05
    ily
    -0.05
    POSITIVE LOGITS
     deeds
    0.10
    ness
    0.10
     intentions
    0.09
    intent
    0.09
    illance
    0.09
     things
    0.08
     deed
    0.08
    nes
    0.08
    Intent
    0.08
     Intent
    0.08
    Activations Density 0.020%

    No Known Activations