© 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. 119720
    Prev
    Next
    INDEX
    Explanations

    the presence of "we" or similar first-person plural pronouns

    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
    mé
    -0.06
    try
    -0.06
    afa
    -0.06
    isia
    -0.06
    _ipv
    -0.06
    lle
    -0.06
     Kov
    -0.06
    ùi
    -0.06
    avanaugh
    -0.06
    enser
    -0.06
    POSITIVE LOGITS
    osy
    0.08
    ais
    0.07
    ust
    0.07
    á»ĭp
    0.07
    .ArgumentParser
    0.07
     previously
    0.07
    ãĥ©ãĤ¤ãĥ³
    0.07
     proposal
    0.06
     elsewhere
    0.06
    à¥ĭà¤Ł
    0.06
    Activations Density 0.055%

    No Known Activations