© 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. 14643
    Prev
    Next
    INDEX
    Explanations

    references to specific institutions, locations, and entities, particularly in legal and educational contexts

    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
    okies
    -0.06
    /system
    -0.06
    atable
    -0.06
    ancellable
    -0.06
    ./(
    -0.06
    linger
    -0.06
    /sites
    -0.06
    ÑĤаж
    -0.06
    ihil
    -0.06
    uzey
    -0.06
    POSITIVE LOGITS
     Pradesh
    0.07
    ëĮĢíķĻêµIJ
    0.07
    macen
    0.07
     Ãľniversitesi
    0.07
    /manual
    0.07
    vara
    0.07
    -feira
    0.07
     magazine
    0.07
    ewire
    0.06
    meer
    0.06
    Activations Density 0.544%

    No Known Activations