© 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. 85075
    Prev
    Next
    INDEX
    Explanations

    the term "Inc" indicating incorporation in companies or organizations

    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
    las
    -0.06
    ondo
    -0.06
    -proof
    -0.06
    proof
    -0.06
    ingu
    -0.06
    ково
    -0.06
    irit
    -0.06
    ìļ´ëį°
    -0.06
    ijľ
    -0.06
    vertising
    -0.05
    POSITIVE LOGITS
    ï¸ı
    0.11
    /Foundation
    0.09
    opor
    0.08
    èij£äºĭ
    0.08
    orp
    0.08
    ognito
    0.07
    flater
    0.07
    oran
    0.07
     Spi
    0.07
    mbH
    0.07
    Activations Density 0.014%

    No Known Activations