© 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. 17-LLAMASCOPE-RES-131K
    11. 30455
    Prev
    Next
    INDEX
    Explanations

    phrases related to fields of study or areas of interest

    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
    tainment
    -0.09
    uien
    -0.07
    abbr
    -0.07
    ürn
    -0.07
    435
    -0.06
    dsn
    -0.06
    dess
    -0.06
    privation
    -0.06
    locator
    -0.06
    dating
    -0.06
    POSITIVE LOGITS
     areas
    0.11
    Areas
    0.09
     area
    0.08
     Areas
    0.08
    areas
    0.08
     expertise
    0.08
     fields
    0.08
     domains
    0.07
     interests
    0.07
     subjects
    0.07
    Activations Density 0.012%

    No Known Activations