© 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. 40001
    Prev
    Next
    INDEX
    Explanations

    descriptors of professional services and business credibility

    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
    astos
    -0.07
    PIO
    -0.07
    ignKey
    -0.07
     ÑħÑĢа
    -0.07
    lund
    -0.06
    Td
    -0.06
    _ASSUME
    -0.06
    alama
    -0.06
    биÑĤ
    -0.06
    efs
    -0.06
    POSITIVE LOGITS
     company
    0.08
     firm
    0.08
     agency
    0.06
     modern
    0.06
     founded
    0.06
    ¥
    0.06
    704
    0.06
     outfit
    0.06
     ethical
    0.06
    ä¼ļ社
    0.06
    Activations Density 0.025%

    No Known Activations