© 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. 5-LLAMASCOPE-RES-131K
    11. 125522
    Prev
    Next
    INDEX
    Explanations

    articles preceding nouns, suggesting a focus on grammatical structure

    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
    -plugins
    -0.06
    villa
    -0.06
    -floating
    -0.06
    gili
    -0.06
    ibli
    -0.06
    ring
    -0.06
    -plugin
    -0.06
    _challenge
    -0.06
     Hera
    -0.06
    _VAL
    -0.06
    POSITIVE LOGITS
    é¤
    0.07
    culate
    0.07
    ubat
    0.07
    -toggle
    0.07
     Decompiled
    0.07
    udence
    0.06
     certain
    0.06
     Mother
    0.06
    ẩm
    0.06
    ionage
    0.06
    Activations Density 0.012%

    No Known Activations