© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 90778
    Prev
    Next
    INDEX
    Explanations

    phrases that describe economic systems and societal conditions

    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
    stad
    -0.06
    angan
    -0.06
     behalf
    -0.06
    046
    -0.06
    rikes
    -0.06
     keeping
    -0.06
    venes
    -0.06
     Dense
    -0.06
    iration
    -0.05
     hint
    -0.05
    POSITIVE LOGITS
    üstü
    0.08
    opleft
    0.08
    verse
    0.08
    .setViewport
    0.08
    Sharper
    0.08
    Ñħодим
    0.07
     REFER
    0.07
    ObjectName
    0.07
    PÅĻed
    0.07
    ìĿ´ë¹Ħ
    0.07
    Activations Density 0.028%

    No Known Activations