© 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. 38221
    Prev
    Next
    INDEX
    Explanations

    references to public-private partnerships

    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
    ToUpper
    -0.07
    ittel
    -0.07
    UnderTest
    -0.06
    /fixtures
    -0.06
    _startup
    -0.06
    æ¡IJ
    -0.06
    _HINT
    -0.06
     ฿
    -0.06
     Kavanaugh
    -0.06
    tru
    -0.06
    POSITIVE LOGITS
     concept
    0.08
     Maker
    0.08
    -style
    0.07
    ee
    0.07
    esModule
    0.06
     formation
    0.06
    Maker
    0.06
    -maker
    0.06
    ÃŃst
    0.06
    ees
    0.06
    Activations Density 0.031%

    No Known Activations