© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83298
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and their related 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
    exus
    -0.07
     reactive
    -0.07
    оби
    -0.07
     Reactive
    -0.07
    ault
    -0.07
     باÙĦÙĨ
    -0.07
    кеÑĤ
    -0.06
     ä½ı
    -0.06
    ìĪ
    -0.06
    á»IJ
    -0.06
    POSITIVE LOGITS
    ansson
    0.06
    409
    0.06
    ermen
    0.06
     GS
    0.06
     DIM
    0.06
     Barg
    0.06
     permalink
    0.06
    CUS
    0.06
    strand
    0.06
     Perf
    0.06
    Activations Density 0.047%

    No Known Activations