© 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. 126480
    Prev
    Next
    INDEX
    Explanations

    references to local culture and geography

    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
    KERNEL
    -0.06
    IMITIVE
    -0.06
    олай
    -0.06
    олеÑĤ
    -0.06
     mount
    -0.06
    inz
    -0.06
     Whatsapp
    -0.06
    umbling
    -0.06
     primitive
    -0.06
    uan
    -0.06
    POSITIVE LOGITS
    atern
    0.07
     ìĦľìļ¸íĬ¹ë³Ħìĭľ
    0.06
     rit
    0.06
    ãĥ³ãĥĦ
    0.06
     Mitar
    0.06
    lamaz
    0.06
    'n
    0.06
    ache
    0.06
    uchi
    0.06
    /templates
    0.06
    Activations Density 0.000%

    No Known Activations