© 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. 58186
    Prev
    Next
    INDEX
    Explanations

    phrases related to awareness and its promotion

    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
    uted
    -0.08
    ura
    -0.08
    WithValue
    -0.07
    cert
    -0.07
    ivial
    -0.07
    rolled
    -0.07
    øj
    -0.07
    Çİ
    -0.07
    ework
    -0.07
     moci
    -0.07
    POSITIVE LOGITS
    es
    0.10
    s
    0.10
    fulness
    0.09
    ness
    0.08
    -ra
    0.07
    ance
    0.07
    iveness
    0.06
    fade
    0.06
     levels
    0.06
     awareness
    0.06
    Activations Density 0.007%

    No Known Activations