© 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. 17-LLAMASCOPE-RES-131K
    11. 61503
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding political and military interventions

    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
     patriot
    -0.07
    олов
    -0.07
    MSN
    -0.07
    ulas
    -0.07
    ousse
    -0.07
    enko
    -0.07
     Hust
    -0.07
    PTR
    -0.07
    aben
    -0.07
    ÙĨدÛĮ
    -0.07
    POSITIVE LOGITS
    agt
    0.08
     stability
    0.07
     stable
    0.07
     instability
    0.07
     unstable
    0.06
    atitude
    0.06
     Stability
    0.06
    ag
    0.06
    stable
    0.06
    enis
    0.06
    Activations Density 0.028%

    No Known Activations