© 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. 85246
    Prev
    Next
    INDEX
    Explanations

    mentions of academic institutions and their associated fields

    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
    assic
    -0.07
    iegel
    -0.06
     flow
    -0.06
    onto
    -0.06
     pers
    -0.06
     (
    -0.06
    pear
    -0.06
    еÑĢб
    -0.06
    rego
    -0.06
     Lama
    -0.06
    POSITIVE LOGITS
     tesis
    0.07
    ,},↵
    0.07
    CACHE
    0.07
    é³´
    0.07
    raž
    0.07
    647
    0.07
    ÑĤеÑĢ
    0.07
     semiclass
    0.07
    bib
    0.07
    oley
    0.07
    Activations Density 0.001%

    No Known Activations