© 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. 28533
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific disciplines and methodologies

    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
    abbo
    -0.09
     ///<
    -0.08
    reater
    -0.07
     acos
    -0.07
    entar
    -0.07
     nét
    -0.07
    าà¸ģร
    -0.07
    sworth
    -0.07
     khá»ıi
    -0.07
    istrovstvÃŃ
    -0.07
    POSITIVE LOGITS
     applied
    0.07
     applications
    0.06
    ists
    0.06
     Umb
    0.06
     Applications
    0.06
    ons
    0.06
     Nug
    0.06
    strap
    0.06
     aspects
    0.05
     unpl
    0.05
    Activations Density 0.046%

    No Known Activations