© 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. 30162
    Prev
    Next
    INDEX
    Explanations

    references to physical objects and their spatial relationships

    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
    811
    -0.07
    eus
    -0.07
    å¤ļãģĦ
    -0.07
    thy
    -0.06
    /opt
    -0.06
    ÄŁan
    -0.06
    thalm
    -0.06
    aeda
    -0.06
    jin
    -0.06
    connexion
    -0.06
    POSITIVE LOGITS
    gem
    0.07
     thereof
    0.07
     ÄĮer
    0.07
    clar
    0.07
    ocket
    0.06
     tow
    0.06
    ead
    0.06
    enville
    0.06
    Sdk
    0.06
    thest
    0.06
    Activations Density 0.028%

    No Known Activations