© 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. 15-LLAMASCOPE-RES-131K
    11. 560
    Prev
    Next
    INDEX
    Explanations

    references to the second person "you" in various contexts

    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
    .firebaseapp
    -0.07
     lon
    -0.06
    ottes
    -0.06
    Spi
    -0.06
    .tc
    -0.06
    edn
    -0.06
    eni
    -0.06
     Dude
    -0.06
    aky
    -0.06
    kop
    -0.06
    POSITIVE LOGITS
     can
    0.10
     Tide
    0.07
    że
    0.07
     Wade
    0.07
     Pa
    0.06
    can
    0.06
    åı¯ä»¥
    0.06
     Can
    0.06
     liebe
    0.06
    umpt
    0.06
    Activations Density 0.036%

    No Known Activations