© 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. 74030
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to inspection, governance, and leadership

    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
    .jp
    -0.06
    неÑģ
    -0.06
     jorn
    -0.06
    ers
    -0.06
     disap
    -0.06
    _INCLUDED
    -0.06
    ylvania
    -0.06
    _DEFINE
    -0.06
    esian
    -0.06
    Importer
    -0.06
    POSITIVE LOGITS
    -general
    0.09
    -General
    0.08
     general
    0.08
     Emer
    0.08
     General
    0.07
    ship
    0.07
    ate
    0.07
    adb
    0.07
    eneral
    0.07
    ships
    0.06
    Activations Density 0.034%

    No Known Activations