© 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. 15-LLAMASCOPE-RES-131K
    6. 61604
    Prev
    Next
    INDEX
    Explanations

    expressions related to artificial intelligence and its capabilities

    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
    leh
    -0.08
    ampler
    -0.07
    ouz
    -0.07
    èĻİ
    -0.07
    ¬ģ
    -0.07
    lep
    -0.07
    fte
    -0.07
    ÏĥÏĩ
    -0.07
    codegen
    -0.07
    è°
    -0.07
    POSITIVE LOGITS
     intelligence
    0.10
     intelligent
    0.09
     Intelligence
    0.09
    intelligence
    0.08
     IQ
    0.07
     Intelligent
    0.07
     sophisticated
    0.07
     Flex
    0.06
     intelig
    0.06
     independently
    0.06
    Activations Density 0.064%

    No Known Activations