© 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. 56566
    Prev
    Next
    INDEX
    Explanations

    interactions and transformations in physical systems, particularly in relation to particle dynamics and field behaviors

    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
    976
    -0.07
    itol
    -0.07
    itom
    -0.07
    Invoker
    -0.06
    IF
    -0.06
    orda
    -0.06
     tol
    -0.06
    cul
    -0.06
     Vie
    -0.06
    esub
    -0.06
    POSITIVE LOGITS
    ibel
    0.07
    IDGET
    0.06
    .weixin
    0.06
    اطر
    0.06
     along
    0.06
    ncmp
    0.06
    YST
    0.06
     ëĶ¸
    0.06
    ë¹Į
    0.06
    ptime
    0.06
    Activations Density 0.086%

    No Known Activations