© 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. 104100
    Prev
    Next
    INDEX
    Explanations

    references to technical specifications and data formats

    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
    rim
    -0.08
    defgroup
    -0.07
    amac
    -0.07
    sek
    -0.07
    ands
    -0.07
    erule
    -0.07
    apat
    -0.07
    raç
    -0.06
    ç¼
    -0.06
    olis
    -0.06
    POSITIVE LOGITS
    olley
    0.06
    ãĤ¹ãĤ¯
    0.06
    ï¸
    0.06
     Bl
    0.06
     bid
    0.06
     Prospect
    0.05
     intrusive
    0.05
     Spark
    0.05
     Dresses
    0.05
     enjoyed
    0.05
    Activations Density 0.077%

    No Known Activations