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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74302
    Prev
    Next
    INDEX
    Explanations

    concepts related to economic development and growth

    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
    agas
    -0.08
    swick
    -0.07
    áš
    -0.07
    айд
    -0.07
    SGlobal
    -0.07
    &eacute
    -0.07
    /global
    -0.07
    entiful
    -0.07
    seau
    -0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.07
    POSITIVE LOGITS
     reforms
    0.07
     growth
    0.07
     reform
    0.06
     capital
    0.06
     country
    0.06
     Reform
    0.06
    igen
    0.06
    Anchor
    0.06
     skills
    0.06
    ecd
    0.06
    Activations Density 0.003%

    No Known Activations