© 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. 31543
    Prev
    Next
    INDEX
    Explanations

    references to gourmet dining experiences and restaurant details

    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
     indexed
    -0.07
     spill
    -0.06
     CG
    -0.06
    ãĤħ
    -0.06
     Cust
    -0.06
     thirsty
    -0.06
     primary
    -0.06
     åĴ
    -0.06
    ãģ®ãģĭ
    -0.06
    Splash
    -0.06
    POSITIVE LOGITS
    cul
    0.08
    isel
    0.07
     courses
    0.07
    enuity
    0.07
    chef
    0.07
    Course
    0.07
     chef
    0.07
     kraj
    0.06
    course
    0.06
     Courses
    0.06
    Activations Density 0.025%

    No Known Activations