© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84936
    Prev
    Next
    INDEX
    Explanations

    specific quantitative measures and requirements related to emissions and infrastructure

    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
    é¦Ļ
    -0.06
    ffen
    -0.06
    vala
    -0.05
     pretext
    -0.05
    emek
    -0.05
    iento
    -0.05
    ÛĮØ·
    -0.05
     rast
    -0.05
     localVar
    -0.05
     Exhaust
    -0.05
    POSITIVE LOGITS
     needed
    0.17
     required
    0.16
     needs
    0.16
    Needed
    0.15
     Needed
    0.15
     Required
    0.15
    needed
    0.15
     necessary
    0.15
    needs
    0.15
     need
    0.15
    Activations Density 0.054%

    No Known Activations