© 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. 28443
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "in" and related prepositional phrases

    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
    utsche
    -0.07
    ικα
    -0.07
     ÑĨÑı
    -0.07
    ден
    -0.07
     muschi
    -0.07
     pÅĻiÄįemž
    -0.07
    ynchronously
    -0.07
    eria
    -0.07
    درÛĮ
    -0.06
    ÐĶÐļ
    -0.06
    POSITIVE LOGITS
    /of
    0.07
    ahat
    0.07
    lain
    0.06
     themselves
    0.06
    ATUS
    0.06
     which
    0.06
    æĢ§çļĦ
    0.06
    IGHL
    0.06
    Essay
    0.06
    ÑĢод
    0.06
    Activations Density 0.054%

    No Known Activations