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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 44238
    Prev
    Next
    INDEX
    Explanations

    topics related to management, research, and various sectors within economics

    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
    endon
    -0.06
    !.
    -0.05
    !!.
    -0.05
     Roose
    -0.05
     Mayo
    -0.05
     Revelation
    -0.05
     Escorts
    -0.05
    â̦.↵↵
    -0.05
     Loft
    -0.05
     Revel
    -0.05
    POSITIVE LOGITS
     Policy
    0.08
    Policy
    0.08
     Economics
    0.08
     economics
    0.08
    Govern
    0.08
     Governance
    0.08
    -general
    0.08
     policy
    0.07
    Finance
    0.07
    -policy
    0.07
    Activations Density 0.028%

    No Known Activations