© 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. 62382
    Prev
    Next
    INDEX
    Explanations

    phrases that contain various forms of self-reflection and self-awareness

    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
    ato
    -0.07
    اÙĦÙĬ
    -0.06
    ESCO
    -0.06
    atos
    -0.06
    esco
    -0.06
    uito
    -0.06
    arters
    -0.06
    ìļ°
    -0.06
    alnız
    -0.05
    णन
    -0.05
    POSITIVE LOGITS
    RIA
    0.08
     typical
    0.08
     modern
    0.07
     moderne
    0.07
    ovic
    0.07
     ÑģовÑĢем
    0.07
    çݰ代
    0.07
     Modern
    0.06
     Reeves
    0.06
    azzo
    0.06
    Activations Density 0.089%

    No Known Activations