Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5181
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms related to international transactions and agreements

    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
    ARA
    -0.07
    074
    -0.06
    059
    -0.06
    ising
    -0.06
    049
    -0.06
     others
    -0.06
    043
    -0.06
    084
    -0.06
     mans
    -0.06
    029
    -0.06
    POSITIVE LOGITS
     minister
    0.08
     Minister
    0.08
     Foreign
    0.07
     foreign
    0.07
     Cabinet
    0.07
     PM
    0.07
     FOREIGN
    0.07
     Ministry
    0.07
     cabinet
    0.07
     President
    0.07
    Activations Density 0.018%

    No Known Activations