© 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. 1405
    Prev
    Next
    INDEX
    Explanations

    address-related terms and components

    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
    coni
    -0.08
    olly
    -0.07
    á»ĵn
    -0.07
    ollipop
    -0.07
    bourg
    -0.07
    ково
    -0.07
    iore
    -0.07
    zem
    -0.07
    ãģĭãĤĬ
    -0.06
    .jp
    -0.06
    POSITIVE LOGITS
    Suite
    0.07
    acons
    0.07
     Cellular
    0.07
     Tropical
    0.06
    maz
    0.06
     âĢª
    0.06
     cellular
    0.06
     Suite
    0.06
    ISR
    0.06
    @testable
    0.06
    Activations Density 0.016%

    No Known Activations