© 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. 121389
    Prev
    Next
    INDEX
    Explanations

    concepts related to networks and their structural properties

    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
    buat
    -0.08
    nant
    -0.07
    aupt
    -0.07
    theid
    -0.07
    .CreateInstance
    -0.06
    _integration
    -0.06
    agua
    -0.06
    ptive
    -0.06
    .sdk
    -0.06
    raq
    -0.06
    POSITIVE LOGITS
     social
    0.11
     network
    0.10
     networks
    0.09
    -network
    0.09
     Social
    0.09
    network
    0.09
     community
    0.08
    social
    0.08
    /network
    0.08
    Network
    0.08
    Activations Density 0.141%

    No Known Activations