© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77958
    Prev
    Next
    INDEX
    Explanations

    instances of location-related terms or phrases

    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
    atti
    -0.07
    zend
    -0.07
    grave
    -0.07
    reed
    -0.07
    utton
    -0.07
    ulu
    -0.06
    coop
    -0.06
    etter
    -0.06
    olta
    -0.06
    ihn
    -0.06
    POSITIVE LOGITS
    ëĦ·
    0.06
    ÙħÙĨد
    0.06
     Mick
    0.06
    ALCHEMY
    0.06
    ilde
    0.06
     íĤ
    0.06
    asename
    0.06
    ãĥ³ãĥĸ
    0.06
     ÐļÑĢи
    0.06
    डर
    0.06
    Activations Density 0.001%

    No Known Activations