© 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. 86478
    Prev
    Next
    INDEX
    Explanations

    phrases related to control and power dynamics

    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
    anki
    -0.08
    lesi
    -0.08
    readcr
    -0.07
    aña
    -0.07
    rush
    -0.07
    aeda
    -0.07
    ctors
    -0.07
     intermedi
    -0.07
    atorium
    -0.07
    alama
    -0.07
    POSITIVE LOGITS
     nackte
    0.07
    504
    0.07
    ick
    0.07
     ⣨
    0.06
    agu
    0.06
    iek
    0.06
     Alexis
    0.06
    324
    0.06
     Hazard
    0.06
    steller
    0.06
    Activations Density 0.002%

    No Known Activations