© 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. 61864
    Prev
    Next
    INDEX
    Explanations

    concepts related to democratic governance and virtual societies

    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
    foy
    -0.08
    lemn
    -0.08
    ä¼Ļ
    -0.08
    nech
    -0.07
    رخ
    -0.07
    è§
    -0.07
    çŁ
    -0.07
    ($)
    -0.07
    /portfolio
    -0.07
    colm
    -0.07
    POSITIVE LOGITS
     consensus
    0.07
     voting
    0.06
     community
    0.06
    ansk
    0.05
     literally
    0.05
     tang
    0.05
    .org
    0.05
     Lesser
    0.05
     compromise
    0.05
     labour
    0.05
    Activations Density 0.001%

    No Known Activations