© 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. 61275
    Prev
    Next
    INDEX
    Explanations

    references to language and writing systems, particularly regarding Chinese characters

    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
    .NULL
    -0.07
    ikel
    -0.07
    .community
    -0.06
    мин
    -0.06
    .boost
    -0.06
    verb
    -0.06
    ekl
    -0.06
    ikk
    -0.06
    ustos
    -0.06
    _phys
    -0.06
    POSITIVE LOGITS
    gree
    0.07
     functools
    0.06
    303
    0.06
     guessing
    0.06
     Incoming
    0.06
    ัà¸ģษ
    0.06
    uli
    0.06
    udoku
    0.06
    _ISR
    0.06
    igte
    0.06
    Activations Density 0.010%

    No Known Activations