© 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. 63272
    Prev
    Next
    INDEX
    Explanations

    HTML meta tags and document structure 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
    astreet
    -0.07
    ysa
    -0.06
    icensed
    -0.06
    asca
    -0.06
     Mend
    -0.06
    iren
    -0.06
     taken
    -0.06
     Haskell
    -0.06
    .scalablytyped
    -0.06
    /dist
    -0.06
    POSITIVE LOGITS
    gli
    0.07
    andbox
    0.06
    ê´Ģ
    0.06
    uchs
    0.06
    NSS
    0.06
    .crm
    0.06
    ills
    0.06
    ãĥĪãĥ«
    0.06
    ãĥ
    0.06
    ê°Ŀ
    0.06
    Activations Density 0.001%

    No Known Activations