© 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. 78813
    Prev
    Next
    INDEX
    Explanations

    financial data and economic figures

    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
    æ¼
    -0.07
    urr
    -0.06
    zt
    -0.06
    ضÙħ
    -0.06
     mathematic
    -0.06
    ÙIJÙij
    -0.06
    Poster
    -0.06
    égor
    -0.06
    zech
    -0.06
     impro
    -0.06
    POSITIVE LOGITS
    ecd
    0.07
     atIndex
    0.07
    enville
    0.06
    writes
    0.06
    xffffff
    0.06
    ensing
    0.06
    ActivityResult
    0.06
    olygon
    0.06
    oldem
    0.06
    nad
    0.06
    Activations Density 0.003%

    No Known Activations