© 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. 80660
    Prev
    Next
    INDEX
    Explanations

    colons followed by numerical values or annotations

    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
    upp
    -0.07
    iddy
    -0.07
    azzo
    -0.07
    yan
    -0.06
    ród
    -0.06
    quee
    -0.06
     Hann
    -0.06
     Station
    -0.06
    æĤ£
    -0.06
    ury
    -0.06
    POSITIVE LOGITS
     gezocht
    0.07
    оÑĪ
    0.07
    udget
    0.06
    ë¹ĦìķĦ
    0.06
    atism
    0.06
    stva
    0.06
     sn
    0.06
    lds
    0.06
    Fully
    0.06
    cta
    0.06
    Activations Density 0.001%

    No Known Activations