© 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. 91529
    Prev
    Next
    INDEX
    Explanations

    information related to notable achievements and historical figures

    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
    è¡Ľ
    -0.07
     Eisen
    -0.06
     compat
    -0.06
    197
    -0.06
     rarity
    -0.06
    edian
    -0.06
     satellite
    -0.06
    rais
    -0.06
    emma
    -0.06
    -lfs
    -0.05
    POSITIVE LOGITS
     flyers
    0.09
     flight
    0.09
     Flyers
    0.08
     flying
    0.08
    ahoma
    0.08
     Flight
    0.08
    Flight
    0.08
    flutter
    0.07
     flyer
    0.07
     aviation
    0.07
    Activations Density 0.012%

    No Known Activations