© 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. 85175
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal and societal expectations, particularly in the context of ambition and perfectionism

    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
    KeyId
    -0.07
    ign
    -0.07
     GiỼi
    -0.07
    rane
    -0.07
    ift
    -0.07
    Idle
    -0.07
    idar
    -0.07
    azio
    -0.07
    anz
    -0.07
    oucher
    -0.07
    POSITIVE LOGITS
     perfection
    0.08
     tendencies
    0.07
     Type
    0.07
     tendency
    0.07
     control
    0.07
     compuls
    0.07
     martyr
    0.07
     syndrome
    0.07
     personality
    0.07
     Personality
    0.06
    Activations Density 0.069%

    No Known Activations