© 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. 31731
    Prev
    Next
    INDEX
    Explanations

    phrases related to event registration and discounts

    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
    807
    -0.06
    UniqueId
    -0.06
     ÄĮeská
    -0.06
    riers
    -0.06
    ç§ģ
    -0.05
     Brand
    -0.05
    ulta
    -0.05
     ex
    -0.05
     Roberts
    -0.05
    asher
    -0.05
    POSITIVE LOGITS
     Early
    0.09
    Early
    0.09
     Incontri
    0.08
     early
    0.07
    undle
    0.07
    gress
    0.07
    early
    0.07
    éĺ¶æ®µ
    0.07
    raphics
    0.07
     æĹ
    0.07
    Activations Density 0.004%

    No Known Activations