© 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. 17-LLAMASCOPE-RES-131K
    6. 3030
    Prev
    Next
    INDEX
    Explanations

    first-person and second-person pronouns and their uses in context

    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
    cheid
    -0.07
    ugar
    -0.07
    ỹ
    -0.07
     chalk
    -0.06
    emailer
    -0.06
    aja
    -0.06
    hm
    -0.06
     Feder
    -0.06
    tain
    -0.06
    üf
    -0.06
    POSITIVE LOGITS
     liked
    0.08
     interested
    0.07
     interess
    0.07
    engo
    0.07
     Howe
    0.07
    504
    0.06
     interest
    0.06
    601
    0.06
    åĸľæ¬¢
    0.06
    suit
    0.06
    Activations Density 0.018%

    No Known Activations