© 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. 116333
    Prev
    Next
    INDEX
    Explanations

    references to growth or progression from one state to another

    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
    zzo
    -0.06
     kraje
    -0.06
    ee
    -0.06
    Щ
    -0.06
    ersh
    -0.06
    quot
    -0.06
     авÑĤомаÑĤи
    -0.06
     bü
    -0.06
    irl
    -0.06
    umat
    -0.06
    POSITIVE LOGITS
     mere
    0.11
     initially
    0.11
     initial
    0.10
    mere
    0.09
     merely
    0.09
    æľĢåĪĿ
    0.09
     simple
    0.09
    Initially
    0.09
     Initially
    0.09
     inicial
    0.08
    Activations Density 0.013%

    No Known Activations