© 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 EvalsExportsinterp-engineNEWAPI 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. 95300
    Prev
    Next
    INDEX
    Explanations

    references to the decline of American global influence

    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
    utsche
    -0.07
    UBE
    -0.07
    reau
    -0.07
    utura
    -0.07
    esian
    -0.07
     nuts
    -0.06
     PyTuple
    -0.06
     ÑĥÑĢож
    -0.06
     Highlander
    -0.06
    ìĿ´íĦ°
    -0.06
    POSITIVE LOGITS
     Pax
    0.09
     empire
    0.09
     greatness
    0.08
     power
    0.08
     heg
    0.08
     dominance
    0.08
    power
    0.08
     Empire
    0.07
     domination
    0.07
    å¸ĿåĽ½
    0.07
    Activations Density 0.181%

    No Known Activations