© 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. 91717
    Prev
    Next
    INDEX
    Explanations

    mentions of specific news articles or features

    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
    سÙĥ
    -0.07
    ference
    -0.06
    746
    -0.06
    lez
    -0.06
    rats
    -0.06
    ÅĻeb
    -0.06
     wh
    -0.06
    ÅĻÃŃž
    -0.06
     PIE
    -0.06
    izard
    -0.06
    POSITIVE LOGITS
     article
    0.08
    /watch
    0.07
     stories
    0.07
     articles
    0.07
    ibar
    0.07
    VERTISEMENT
    0.07
     histories
    0.07
    ober
    0.06
    arak
    0.06
     massaggi
    0.06
    Activations Density 0.014%

    No Known Activations