© 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 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. 3606
    Prev
    Next
    INDEX
    Explanations

    geographic locations related to universities

    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
     Eston
    -0.09
     FreeBSD
    -0.07
     Suffolk
    -0.07
     Delaware
    -0.07
    PEAT
    -0.07
    isque
    -0.07
     Essex
    -0.06
     Joi
    -0.06
    zsche
    -0.06
    aque
    -0.06
    POSITIVE LOGITS
     Munich
    0.11
     Bav
    0.10
     Bayern
    0.10
     Karnataka
    0.10
     München
    0.09
     Southwest
    0.08
    Minnesota
    0.08
     Tucson
    0.07
     Minnesota
    0.07
     mushroom
    0.07
    Activations Density 0.024%

    No Known Activations