© 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. 91518
    Prev
    Next
    INDEX
    Explanations

    references to various types of services

    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
    ãģĬãĤĬ
    -0.10
    soever
    -0.09
    tras
    -0.08
    xin
    -0.08
    è¾°
    -0.07
    wort
    -0.07
    enda
    -0.07
    te
    -0.07
    avin
    -0.07
    s
    -0.07
    POSITIVE LOGITS
     provider
    0.08
    /product
    0.08
    ive
    0.08
    /products
    0.08
    (Service
    0.08
     providers
    0.07
     Provider
    0.07
    provider
    0.07
    imonial
    0.07
    MOOTH
    0.07
    Activations Density 0.061%

    No Known Activations