© 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. 15643
    Prev
    Next
    INDEX
    Explanations

    references to performance metrics and evaluations in competitive contexts

    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
    .scalablytyped
    -0.09
    eyle
    -0.08
    IRR
    -0.07
    вад
    -0.07
    _pickle
    -0.07
     ÐĴики
    -0.07
    ÙħاÙħ
    -0.07
    BoxLayout
    -0.07
    ecko
    -0.07
    заб
    -0.07
    POSITIVE LOGITS
    ãĥģãĥ¼ãĥł
    0.08
     Team
    0.07
     team
    0.07
     teams
    0.07
    omo
    0.06
     crew
    0.06
    577
    0.06
    embers
    0.06
    ing
    0.06
     management
    0.06
    Activations Density 0.038%

    No Known Activations