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

    Neuronpedia

    Jacobian LensNEW
    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. 77306
    Prev
    Next
    INDEX
    Explanations

    topics related to political entities and international relations

    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
     T
    -0.07
    arda
    -0.06
     B
    -0.06
     ali
    -0.06
    elle
    -0.05
     b
    -0.05
     Hot
    -0.05
     Lust
    -0.05
    strand
    -0.05
    _TRUNC
    -0.05
    POSITIVE LOGITS
    urger
    0.08
    utm
    0.08
     UIGraphics
    0.08
    undan
    0.08
    usher
    0.08
    uther
    0.07
     ãĥ´
    0.07
     ucwords
    0.07
    untime
    0.07
    UInteger
    0.07
    Activations Density 0.016%

    No Known Activations