© 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. 63265
    Prev
    Next
    INDEX
    Explanations

    references to mathematical variables and operations within a context

    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
     pis
    -0.06
    ods
    -0.06
    otton
    -0.06
    anford
    -0.06
     mund
    -0.06
     Gram
    -0.06
    lds
    -0.06
    P
    -0.06
     Tet
    -0.06
     sona
    -0.06
    POSITIVE LOGITS
     aforementioned
    0.11
    ĶåĽŀ
    0.09
    éĤ£ä¸ª
    0.09
     вÑĭÑĪе
    0.07
    portun
    0.07
    áŁĴáŀ
    0.07
    APON
    0.07
     afore
    0.07
     MERCHANTABILITY
    0.07
    atre
    0.07
    Activations Density 0.021%

    No Known Activations