© 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. 121472
    Prev
    Next
    INDEX
    Explanations

    references to events, ceremonies, and awards

    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
    оÑģÑĥд
    -0.06
    iger
    -0.06
    aldo
    -0.06
     bath
    -0.06
    heimer
    -0.06
    endant
    -0.06
    ounter
    -0.06
    ÑĨей
    -0.06
    avig
    -0.06
    æļ®
    -0.06
    POSITIVE LOGITS
     alongside
    0.10
    ạt
    0.08
    ÑĢÑıдÑĥ
    0.07
     Morgan
    0.07
    olor
    0.07
    879
    0.06
     personally
    0.06
    iband
    0.06
    eyin
    0.06
    along
    0.06
    Activations Density 0.037%

    No Known Activations