© 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. 116384
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and relationships involving graphs

    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
    主任
    -0.07
     Hicks
    -0.07
    HING
    -0.06
    ertino
    -0.06
    inia
    -0.06
     diren
    -0.06
    .logic
    -0.06
    pragma
    -0.06
    aby
    -0.06
    pector
    -0.06
    POSITIVE LOGITS
     right
    0.06
     volumes
    0.06
     intoxic
    0.06
     left
    0.06
    arih
    0.06
     eg
    0.06
     stamps
    0.06
    åı³
    0.06
     Lehr
    0.06
    859
    0.06
    Activations Density 0.138%

    No Known Activations