© 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. 91563
    Prev
    Next
    INDEX
    Explanations

    terms related to agricultural training and supplies

    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
    acity
    -0.07
    mlin
    -0.06
     zel
    -0.06
    vell
    -0.06
    Thunk
    -0.06
    sterol
    -0.06
     lyon
    -0.06
     Sanat
    -0.06
    Äįást
    -0.06
    ptrdiff
    -0.06
    POSITIVE LOGITS
     inputs
    0.07
     ÙĪر
    0.07
     Inputs
    0.07
     Highland
    0.07
     Escorts
    0.07
    ACCESS
    0.06
    ä¸ĺ
    0.06
    .inputs
    0.06
    çģ
    0.06
    upt
    0.06
    Activations Density 0.017%

    No Known Activations