© 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. 2470
    Prev
    Next
    INDEX
    Explanations

    references to publishing and related entities

    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
     Newspaper
    -0.07
     Seam
    -0.06
    DTV
    -0.06
     entrances
    -0.06
    onda
    -0.06
     Frid
    -0.06
     newspaper
    -0.05
     wrote
    -0.05
    iless
    -0.05
     Leap
    -0.05
    POSITIVE LOGITS
    -books
    0.10
     presses
    0.09
     imprint
    0.09
    books
    0.09
     Publishing
    0.09
    Books
    0.09
     books
    0.09
     publishing
    0.08
     Books
    0.08
    olib
    0.08
    Activations Density 0.023%

    No Known Activations