© 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. 42412
    Prev
    Next
    INDEX
    Explanations

    terms related to aristocracy and aristocratic concepts

    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
    istrovstvÃŃ
    -0.08
    er
    -0.07
    irket
    -0.06
    uling
    -0.06
    bras
    -0.06
    ugin
    -0.06
    anie
    -0.06
    acity
    -0.06
    iec
    -0.06
    lements
    -0.06
    POSITIVE LOGITS
    ivec
    0.09
    otle
    0.09
    emma
    0.08
    otel
    0.07
    andard
    0.07
     Ñģобой
    0.07
     Lud
    0.07
    ocratic
    0.07
    ocrat
    0.07
    ocrats
    0.07
    Activations Density 0.002%

    No Known Activations