© 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. 15-LLAMASCOPE-RES-131K
    11. 88998
    Prev
    Next
    INDEX
    Explanations

    references to schools 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
    umes
    -0.07
    538
    -0.07
     Branch
    -0.07
    961
    -0.06
    iges
    -0.06
    iser
    -0.06
    aho
    -0.06
     fondo
    -0.06
    ing
    -0.06
    ott
    -0.06
    POSITIVE LOGITS
    yard
    0.07
    @Web
    0.07
    оÑĤÑĮ
    0.07
    [$_
    0.07
    ÅĻÃŃž
    0.07
    วล
    0.06
    าà¹Ģล
    0.06
    /tos
    0.06
    mounted
    0.06
    earch
    0.06
    Activations Density 0.019%

    No Known Activations