© 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. 55235
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to value, particularly in economic and business 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
    olon
    -0.07
    ayout
    -0.07
    KB
    -0.06
    ãĥ¼ãĤ¸
    -0.06
    ëģ
    -0.06
    lip
    -0.06
    rate
    -0.06
    olt
    -0.06
    .googlecode
    -0.06
    iger
    -0.06
    POSITIVE LOGITS
    =Value
    0.09
    -added
    0.09
    ForKey
    0.07
    (forKey
    0.07
    çıŃ
    0.07
    åŁŁ
    0.07
    (Value
    0.06
    OF
    0.06
    -nil
    0.06
    andro
    0.06
    Activations Density 0.014%

    No Known Activations