© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78214
    Prev
    Next
    INDEX
    Explanations

    phrases related to business services and economic activities

    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
     businessman
    -0.07
    .metamodel
    -0.07
    اکÛĮ
    -0.07
     виÑģ
    -0.07
    .met
    -0.07
     Mast
    -0.07
     OMIT
    -0.07
     ë³´ë©´
    -0.06
    Ïģιν
    -0.06
    577
    -0.06
    POSITIVE LOGITS
     individuals
    0.08
     government
    0.08
     personal
    0.07
     pleasure
    0.07
     individual
    0.07
    wal
    0.07
    -government
    0.07
     Government
    0.06
    individual
    0.06
     Individuals
    0.06
    Activations Density 0.065%

    No Known Activations