© 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. 96210
    Prev
    Next
    INDEX
    Explanations

    concepts related to sustainability and the integration of sustainable practices into various contexts

    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
    uren
    -0.08
    ÅĻeh
    -0.07
    ersen
    -0.07
    ande
    -0.07
    IRMWARE
    -0.07
    itted
    -0.07
    isp
    -0.06
    uran
    -0.06
    yas
    -0.06
    QualifiedName
    -0.06
    POSITIVE LOGITS
     elements
    0.09
    into
    0.09
     into
    0.09
     element
    0.08
    Into
    0.08
    /embed
    0.08
    elements
    0.07
     principles
    0.07
     Into
    0.07
     principle
    0.06
    Activations Density 0.022%

    No Known Activations