© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129793
    Prev
    Next
    INDEX
    Explanations

    concepts related to consciousness and its relationship to physical reality

    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
    uat
    -0.07
    pedo
    -0.07
    ÙĤت
    -0.07
    edir
    -0.07
    intage
    -0.07
    edn
    -0.07
    à¥ĩय
    -0.07
    utschein
    -0.06
    زاÙĨ
    -0.06
    zone
    -0.06
    POSITIVE LOGITS
     Brain
    0.09
     brain
    0.09
    Brain
    0.09
     Desc
    0.08
    Desc
    0.07
    brain
    0.07
     pup
    0.06
     Physical
    0.06
     puppet
    0.06
    .bc
    0.06
    Activations Density 0.063%

    No Known Activations