© 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. 127022
    Prev
    Next
    INDEX
    Explanations

    references to time durations, particularly those specifying years

    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
     Day
    -0.06
     DevComponents
    -0.06
     inf
    -0.06
    ña
    -0.06
     DAY
    -0.06
    isen
    -0.05
     –
    -0.05
     connections
    -0.05
     day
    -0.05
    preneur
    -0.05
    POSITIVE LOGITS
    iculty
    0.08
    -old
    0.08
    æľŁ
    0.07
    ite
    0.07
    isode
    0.07
    rière
    0.07
    ÃŃsticas
    0.07
    imar
    0.07
    oggled
    0.07
    asty
    0.07
    Activations Density 0.008%

    No Known Activations