© 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 EvalsExportsinterp-engineNEWAPI 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. 17384
    Prev
    Next
    INDEX
    Explanations

    terms related to COVID-19 variants

    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
    éŁ¿
    -0.07
    agher
    -0.07
    âĻ¡
    -0.06
    ?id
    -0.06
     Trigger
    -0.06
     داÙĪ
    -0.06
    å¡
    -0.06
    ctl
    -0.06
    Trigger
    -0.06
    اط
    -0.06
    POSITIVE LOGITS
     ><?
    0.07
     wor
    0.07
    ÑıÑĩ
    0.07
    ersonic
    0.07
     Mour
    0.06
    rell
    0.06
     variants
    0.06
    olan
    0.06
     grown
    0.06
    yar
    0.06
    Activations Density 0.007%

    No Known Activations