© 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. 31636
    Prev
    Next
    INDEX
    Explanations

    references to software development and related concepts

    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
    heit
    -0.08
    ibling
    -0.07
    relude
    -0.07
    ified
    -0.07
    avigate
    -0.07
    LARI
    -0.07
    æł·çļĦ
    -0.07
    BOVE
    -0.07
    heiten
    -0.07
    	fflush
    -0.07
    POSITIVE LOGITS
    afort
    0.07
    /testing
    0.07
    人åijĺ
    0.07
     productivity
    0.06
    /runtime
    0.06
     team
    0.06
    nett
    0.06
     teams
    0.06
    -production
    0.06
    utters
    0.06
    Activations Density 0.010%

    No Known Activations