© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89369
    Prev
    Next
    INDEX
    Explanations

    artifacts and objects associated with historical excavations

    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
    arel
    -0.07
    itore
    -0.07
    quito
    -0.06
    atz
    -0.06
    urat
    -0.06
    ÃŃf
    -0.06
    876
    -0.06
    519
    -0.06
    apore
    -0.06
    ombine
    -0.06
    POSITIVE LOGITS
    ç²¾åĵģ
    0.07
    кÑĢа
    0.07
     Weinstein
    0.07
    IEW
    0.06
    çļ
    0.06
     :č↵
    0.06
     náp
    0.06
    kap
    0.06
     attest
    0.06
    ãĥ¼ãĥ³
    0.06
    Activations Density 0.013%

    No Known Activations