© 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. 69088
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to agricultural practices and fertilizer application

    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
     Zuk
    -0.08
    ogi
    -0.06
     toxins
    -0.06
    ادÙĬØ©
    -0.06
    cury
    -0.06
    uga
    -0.06
    _indent
    -0.06
    onas
    -0.06
    quier
    -0.05
     vis
    -0.05
    POSITIVE LOGITS
     fert
    0.10
     fertilizer
    0.09
     soil
    0.09
     fol
    0.08
     fertil
    0.08
    /feed
    0.08
     Soil
    0.08
    åľŁ
    0.07
    erial
    0.07
    ertil
    0.07
    Activations Density 0.014%

    No Known Activations