© 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. 60027
    Prev
    Next
    INDEX
    Explanations

    quantifiers and approximations related to degree or quantity

    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
    .setRotation
    -0.06
    AAA
    -0.06
    ram
    -0.06
     cÃŃ
    -0.06
    committed
    -0.06
    quist
    -0.06
     Epstein
    -0.06
    272
    -0.06
    qu
    -0.06
    åİ
    -0.06
    POSITIVE LOGITS
    967
    0.07
    enders
    0.06
    iros
    0.06
    LocalizedString
    0.06
    Ctl
    0.06
    umerator
    0.06
     cv
    0.06
    iasi
    0.06
    SystemService
    0.06
     Majority
    0.06
    Activations Density 0.063%

    No Known Activations