© 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. 1446
    Prev
    Next
    INDEX
    Explanations

    references to intelligence and cognitive abilities

    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
    kara
    -0.10
    ursal
    -0.08
    idar
    -0.08
    igli
    -0.08
    benh
    -0.08
    alars
    -0.08
    abi
    -0.07
    æķ
    -0.07
    код
    -0.07
    opal
    -0.07
    POSITIVE LOGITS
     intelligence
    0.08
     Intelligence
    0.08
     scores
    0.07
     IQ
    0.07
     brain
    0.07
     iq
    0.06
     measures
    0.06
     tests
    0.06
     measurement
    0.06
     intellect
    0.06
    Activations Density 0.004%

    No Known Activations