© 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. 77614
    Prev
    Next
    INDEX
    Explanations

    numerical references, particularly years or demographic data

    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
    anus
    -0.06
    exampleInputEmail
    -0.06
    766
    -0.06
    ipe
    -0.06
    ibbon
    -0.06
     ли
    -0.06
    walker
    -0.06
    olars
    -0.06
    senal
    -0.06
    imson
    -0.06
    POSITIVE LOGITS
    quoi
    0.07
    'er
    0.06
    -extra
    0.06
    otti
    0.06
    __/
    0.06
     extr
    0.06
    ëı
    0.06
     expired
    0.06
    unque
    0.06
    extra
    0.06
    Activations Density 0.013%

    No Known Activations