© 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. 16033
    Prev
    Next
    INDEX
    Explanations

    temporal references indicating time periods or durations

    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
    readcr
    -0.08
    tooltip
    -0.07
    bject
    -0.07
    ResourceId
    -0.07
    ynch
    -0.06
    ellig
    -0.06
     millennium
    -0.06
    ibal
    -0.06
    alus
    -0.06
    ickerView
    -0.06
    POSITIVE LOGITS
    ặc
    0.06
    licer
    0.06
    EB
    0.06
     دÙĨ
    0.06
     recent
    0.06
     Downs
    0.06
     Lange
    0.06
    iasi
    0.06
     ago
    0.06
    elsen
    0.06
    Activations Density 0.031%

    No Known Activations