© 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. 30134
    Prev
    Next
    INDEX
    Explanations

    expressions of personal and professional conflict or disagreement

    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
    aldo
    -0.07
    lio
    -0.07
    egra
    -0.07
    lopen
    -0.07
     Voll
    -0.06
    ao
    -0.06
    IVO
    -0.06
    oles
    -0.06
    ammen
    -0.06
    kont
    -0.06
    POSITIVE LOGITS
     publicly
    0.07
    opes
    0.06
    .IT
    0.06
    dish
    0.06
     via
    0.06
    esson
    0.06
    ĺIJ
    0.06
    helm
    0.06
    argest
    0.06
    /Foundation
    0.06
    Activations Density 0.060%

    No Known Activations