© 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. 5834
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intentions or plans

    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
    ymph
    -0.06
     Ferguson
    -0.06
     whereas
    -0.06
     Nor
    -0.05
    amma
    -0.05
    riel
    -0.05
     uranium
    -0.05
    allon
    -0.05
     Lo
    -0.05
    exus
    -0.05
    POSITIVE LOGITS
    eri
    0.08
    scribe
    0.07
     yoksa
    0.07
    PMC
    0.07
    atoria
    0.07
     nÃło
    0.07
     دÛĮÙĨ
    0.06
     gonna
    0.06
     varsa
    0.06
     serious
    0.06
    Activations Density 0.007%

    No Known Activations