© 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. 78887
    Prev
    Next
    INDEX
    Explanations

    topics related to foundational themes and subjects in various narratives

    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
    idon
    -0.07
    ifar
    -0.07
    ongs
    -0.07
    onds
    -0.07
    бол
    -0.07
    osa
    -0.07
    ond
    -0.06
    γκα
    -0.06
    ucci
    -0.06
    anou
    -0.06
    POSITIVE LOGITS
    vier
    0.07
    ä¹ĭä¸Ģ
    0.06
    411
    0.06
    937
    0.06
     Vernon
    0.06
    675
    0.06
     Lah
    0.06
    ÙĦاÙģ
    0.06
     for
    0.06
     vert
    0.06
    Activations Density 0.016%

    No Known Activations