© 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. 123418
    Prev
    Next
    INDEX
    Explanations

    assertions about the development and justification of narrative elements

    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
    baÅŁ
    -0.08
     Multiply
    -0.08
    ucci
    -0.08
    illian
    -0.07
    æ´¥
    -0.07
     BAÅŀ
    -0.07
    ÏĦιÏĥ
    -0.07
    ालय
    -0.07
    /lo
    -0.07
    /cop
    -0.07
    POSITIVE LOGITS
     ever
    0.12
     any
    0.09
     EVER
    0.09
     strictly
    0.09
     usual
    0.08
     anymore
    0.08
     anything
    0.08
    any
    0.07
    Strict
    0.07
     than
    0.07
    Activations Density 0.040%

    No Known Activations