© 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. 15-LLAMASCOPE-RES-131K
    11. 86206
    Prev
    Next
    INDEX
    Explanations

    references to agricultural practices and systems

    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
    onas
    -0.06
    ÃŃ
    -0.06
    ito
    -0.06
    gram
    -0.06
    aire
    -0.06
     komp
    -0.06
     Ital
    -0.06
    oot
    -0.06
    quot
    -0.06
    abb
    -0.05
    POSITIVE LOGITS
    utenberg
    0.07
    OPTION
    0.07
    eneric
    0.07
    авиÑģ
    0.07
    assic
    0.07
    allon
    0.07
    strap
    0.06
    ä¸į足
    0.06
    okens
    0.06
    á»±c
    0.06
    Activations Density 0.067%

    No Known Activations