© 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. 80695
    Prev
    Next
    INDEX
    Explanations

    phrases or constructs that indicate connections or relationships within different contexts

    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
    569
    -0.08
    ÅĻeh
    -0.07
    InstanceOf
    -0.06
    جÙĦ
    -0.06
    643
    -0.06
    zeigen
    -0.06
    elize
    -0.06
    859
    -0.06
    922
    -0.06
    hof
    -0.06
    POSITIVE LOGITS
     Kamp
    0.07
     Wass
    0.07
    nets
    0.06
     DevExpress
    0.06
    idon
    0.06
     pragma
    0.06
    agn
    0.06
    ased
    0.06
    pll
    0.06
    wf
    0.06
    Activations Density 0.010%

    No Known Activations