© 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. 38375
    Prev
    Next
    INDEX
    Explanations

    references to data analytics and metrics

    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
     dise
    -0.06
     tisk
    -0.06
    cko
    -0.06
    aiser
    -0.06
    olvers
    -0.06
    lee
    -0.06
    elage
    -0.06
     memo
    -0.06
    adele
    -0.06
    液
    -0.06
    POSITIVE LOGITS
    ga
    0.08
    GA
    0.07
    Traffic
    0.07
     Collect
    0.07
     ga
    0.07
    Visitor
    0.07
    track
    0.07
    trak
    0.07
    traffic
    0.07
     traffic
    0.07
    Activations Density 0.001%

    No Known Activations