© 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. 27858
    Prev
    Next
    INDEX
    Explanations

    references to scientific publications or studies, particularly focusing on DOIs (Digital Object Identifiers)

    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
    aram
    -0.07
    ellow
    -0.07
     Subcommittee
    -0.07
    ion
    -0.06
    upp
    -0.06
    eck
    -0.06
    uchar
    -0.06
     Ank
    -0.06
    liches
    -0.05
    usat
    -0.05
    POSITIVE LOGITS
    ãģıãģł
    0.08
    ://
    0.08
     Шев
    0.07
     appearances
    0.07
    Scala
    0.07
    लब
    0.07
    oeff
    0.07
    縮
    0.06
    ¶Į
    0.06
    à¥Īद
    0.06
    Activations Density 0.010%

    No Known Activations