© 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. 9-LLAMASCOPE-RES-131K
    11. 95855
    Prev
    Next
    INDEX
    Explanations

    phrases indicating clarification or distinction between concepts

    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
    zan
    -0.07
    زاÙĨ
    -0.06
    /question
    -0.06
    aceut
    -0.06
    ags
    -0.06
    escal
    -0.06
    alet
    -0.06
    asto
    -0.06
    iotics
    -0.06
    achuset
    -0.06
    POSITIVE LOGITS
    ably
    0.08
    437
    0.07
    other
    0.06
    à¥ĩय
    0.06
    pring
    0.06
     cuent
    0.06
    .DialogResult
    0.06
    íķ©
    0.06
    uku
    0.06
     other
    0.05
    Activations Density 0.004%

    No Known Activations