© 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. 108626
    Prev
    Next
    INDEX
    Explanations

    terms related to awards and recognition in industry contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    byss
    -0.07
     Nevada
    -0.06
    磨
    -0.06
    ify
    -0.06
    otel
    -0.06
     ore
    -0.06
     gold
    -0.06
     mij
    -0.06
    iri
    -0.06
     mining
    -0.05
    POSITIVE LOGITS
     virgin
    0.08
    avin
    0.08
     plastic
    0.07
     plastics
    0.07
     polymer
    0.07
    lém
    0.07
    éŁ
    0.07
     melt
    0.07
    opoly
    0.07
     sint
    0.07
    Activations Density 0.066%

    No Known Activations