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

    Neuronpedia

    Jacobian LensNEW
    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. 87458
    Prev
    Next
    INDEX
    Explanations

    statements about the impact of the COVID-19 pandemic on various aspects of life and society

    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
    sg
    -0.07
     Kraj
    -0.07
    oloj
    -0.06
    isk
    -0.06
    oud
    -0.06
    uis
    -0.06
    Ñĩики
    -0.06
    uru
    -0.06
    -addons
    -0.06
    orna
    -0.06
    POSITIVE LOGITS
    rez
    0.07
    ffect
    0.06
    marked
    0.06
     Pins
    0.06
     mass
    0.06
    biz
    0.06
     Thom
    0.06
    irut
    0.06
     accordingly
    0.06
    vincia
    0.06
    Activations Density 0.032%

    No Known Activations