© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86560
    Prev
    Next
    INDEX
    Explanations

    references to nuclear waste management and associated hearings

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    íļ
    -0.07
     neuroscience
    -0.07
     Global
    -0.07
     linker
    -0.06
     Leer
    -0.06
    Global
    -0.06
    .caption
    -0.06
    embro
    -0.06
     Kob
    -0.06
    201
    -0.06
    POSITIVE LOGITS
     USSR
    0.09
    195
    0.08
    196
    0.07
    ï¼ĪæĺŃåĴĮ
    0.07
    ouser
    0.07
    mime
    0.07
    ulti
    0.07
     mime
    0.07
    ousel
    0.07
    BOSE
    0.07
    Activations Density 0.108%

    No Known Activations