© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60820
    Prev
    Next
    INDEX
    Explanations

    references to large companies and their involvement in investment and trade

    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
     discrepan
    -0.07
    abra
    -0.06
    reste
    -0.06
     portions
    -0.06
     calculator
    -0.06
     colomb
    -0.06
    acos
    -0.06
     tip
    -0.06
     lyon
    -0.06
    olog
    -0.06
    POSITIVE LOGITS
    ãĤĪãģĨãģ§ãģĻ
    0.07
    LoadIdentity
    0.07
    ematik
    0.07
     ìŀł
    0.06
    EIF
    0.06
    ienes
    0.06
    igen
    0.06
    æ£ĭ
    0.06
    atten
    0.06
    ertil
    0.06
    Activations Density 0.004%

    No Known Activations