© 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. 57506
    Prev
    Next
    INDEX
    Explanations

    terms associated with institutions, governance, and societal structures

    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
    nul
    -0.08
    spb
    -0.06
    507
    -0.06
    çıŃ
    -0.06
    controllers
    -0.06
     Gram
    -0.06
    nia
    -0.06
     lo
    -0.06
    orias
    -0.06
     partial
    -0.05
    POSITIVE LOGITS
     phenomena
    0.13
     phenomenon
    0.11
     features
    0.09
     feature
    0.08
    features
    0.08
    feature
    0.08
    常
    0.08
     concepts
    0.07
    ares
    0.07
     traits
    0.07
    Activations Density 0.111%

    No Known Activations