© 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. 86134
    Prev
    Next
    INDEX
    Explanations

    sentiments and concerns related to business representation and challenges faced by Australian businesses

    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
    ansk
    -0.07
    illions
    -0.07
     Fol
    -0.07
    menin
    -0.07
    tsky
    -0.07
     llen
    -0.07
    itel
    -0.07
    akk
    -0.07
    ksam
    -0.07
    .$.
    -0.07
    POSITIVE LOGITS
     respectively
    0.08
     outright
    0.06
     currently
    0.06
     overall
    0.06
    errick
    0.06
     Wander
    0.06
     personally
    0.06
    316
    0.05
    ild
    0.05
     general
    0.05
    Activations Density 0.012%

    No Known Activations