© 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. 119912
    Prev
    Next
    INDEX
    Explanations

    technical terms related to nuclear physics and scattering measurements

    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
    _logic
    -0.09
     addCriterion
    -0.08
    rane
    -0.08
    ANNEL
    -0.07
    âĢ«
    -0.07
    azel
    -0.07
    кеÑĤ
    -0.07
     gravid
    -0.07
    lun
    -0.07
     billig
    -0.07
    POSITIVE LOGITS
     parameters
    0.07
     underlying
    0.07
     important
    0.06
     upper
    0.06
     Parameters
    0.06
     key
    0.05
     otherwise
    0.05
     gross
    0.05
     beyond
    0.05
     composition
    0.05
    Activations Density 0.062%

    No Known Activations