© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 71103
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal reflection and introspection

    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
    ezi
    -0.07
     advertise
    -0.07
     åĩº
    -0.06
     imper
    -0.06
     Ka
    -0.06
    cription
    -0.06
    egal
    -0.06
    É
    -0.06
     Hansen
    -0.06
    createClass
    -0.06
    POSITIVE LOGITS
    æĸ°éĹ»
    0.09
     news
    0.09
    -news
    0.08
    .news
    0.08
     daily
    0.07
    news
    0.07
    (news
    0.07
    updates
    0.07
    -source
    0.07
     Nachricht
    0.07
    Activations Density 0.003%

    No Known Activations