© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91688
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between historical figures and events

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    levator
    -0.08
    plib
    -0.07
    ampie
    -0.07
     oci
    -0.07
    agnet
    -0.06
     Monte
    -0.06
    enever
    -0.06
    برÛĮ
    -0.06
    lds
    -0.06
    ucch
    -0.06
    POSITIVE LOGITS
     mand
    0.07
     mandate
    0.06
     Mand
    0.06
     mandates
    0.06
     pent
    0.06
    yield
    0.06
    vol
    0.06
    ìłĪ
    0.06
    uar
    0.06
    mand
    0.05
    Activations Density 0.002%

    No Known Activations