© 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. 83379
    Prev
    Next
    INDEX
    Explanations

    connections between events and their outcomes

    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
    ÏĦιο
    -0.07
    eam
    -0.07
    ضر
    -0.07
    lero
    -0.07
     Conc
    -0.07
    .Override
    -0.07
    ÑģÑĮк
    -0.06
    -mf
    -0.06
    .labelX
    -0.06
    iÄį
    -0.06
    POSITIVE LOGITS
     their
    0.08
     Saturday
    0.06
    argar
    0.06
     Their
    0.06
    680
    0.06
    ÑĪили
    0.06
    utar
    0.06
     Sandwich
    0.06
    Their
    0.05
    mods
    0.05
    Activations Density 0.041%

    No Known Activations