© 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. 1176
    Prev
    Next
    INDEX
    Explanations

    references to "drift" and its variations, along with mentions of specific names like "Drake" and "Druid."

    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
    ãĥ£
    -0.07
    ToDevice
    -0.07
    cntl
    -0.07
    remen
    -0.07
     Blaze
    -0.06
    ichte
    -0.06
    åŁŁ
    -0.06
    dong
    -0.06
    ãĤĩãģĨ
    -0.06
     Injury
    -0.06
    POSITIVE LOGITS
    aper
    0.07
    ugged
    0.07
    ongo
    0.07
    inks
    0.07
    astic
    0.07
     dr
    0.07
    eller
    0.07
    isc
    0.06
    oney
    0.06
    inski
    0.06
    Activations Density 0.019%

    No Known Activations