© 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. 121532
    Prev
    Next
    INDEX
    Explanations

    mentions of shared documents and their statistics, particularly regarding web content and user engagement

    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
     telah
    -0.09
    've
    -0.09
    ’ve
    -0.08
     Äijã
    -0.08
     hebben
    -0.08
    have
    -0.07
     hav
    -0.07
     hasn
    -0.07
     have
    -0.07
    .have
    -0.07
    POSITIVE LOGITS
    ped
    0.07
     Arena
    0.06
     od
    0.06
    Macro
    0.06
    .FindGameObjectWithTag
    0.06
    еÑĢк
    0.06
     Sponge
    0.06
     interval
    0.06
    Barrier
    0.05
    iendo
    0.05
    Activations Density 0.028%

    No Known Activations