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. 44293
    Prev
    Next
    INDEX
    Explanations

    references to economic models and elasticity concepts

    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
    кÑĤа
    -0.08
     Terrain
    -0.07
    YLON
    -0.07
    zdy
    -0.07
     dán
    -0.07
    acific
    -0.07
    MethodManager
    -0.07
    afd
    -0.07
    xBD
    -0.07
    istrovstvÃŃ
    -0.07
    POSITIVE LOGITS
     Ramsey
    0.09
     Wal
    0.09
     consumption
    0.09
     agents
    0.09
     Cobb
    0.08
     agent
    0.08
     CES
    0.08
     asset
    0.08
     overlapping
    0.08
     equilibrium
    0.08
    Activations Density 0.005%

    No Known Activations