© 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. 129287
    Prev
    Next
    INDEX
    Explanations

    terms related to magnetic fields and structures

    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
    Ùĩ
    -0.09
    ska
    -0.08
    keit
    -0.07
    erseniz
    -0.07
     olsun
    -0.07
    ãģĦãĤĭ
    -0.07
    artz
    -0.07
    anke
    -0.07
    eming
    -0.07
    agues
    -0.07
    POSITIVE LOGITS
    ically
    0.09
    ory
    0.08
    ee
    0.07
    ism
    0.07
    ym
    0.07
    ized
    0.07
    ization
    0.07
    ron
    0.07
    iosper
    0.07
    ees
    0.06
    Activations Density 0.007%

    No Known Activations