© 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. 528
    Prev
    Next
    INDEX
    Explanations

    comparative phrases regarding quantities or measurements

    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
    Äįan
    -0.08
    же
    -0.07
    REFER
    -0.07
    idlo
    -0.07
    itational
    -0.07
     CreateTable
    -0.07
    azy
    -0.06
    ạch
    -0.06
    enco
    -0.06
    NoSuch
    -0.06
    POSITIVE LOGITS
    erver
    0.07
     nÃło
    0.07
    rial
    0.06
    ekk
    0.06
    éĻIJ
    0.06
    .UnitTesting
    0.06
     nor
    0.06
    oric
    0.06
    erialize
    0.06
    mind
    0.06
    Activations Density 0.015%

    No Known Activations