© 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. 127214
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the act of spending time

    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
     вÑģÑĤ
    -0.08
    venta
    -0.07
    .EVENT
    -0.07
    udas
    -0.07
    /from
    -0.07
     lá»ĭch
    -0.06
    reon
    -0.06
    TIM
    -0.06
     Immutable
    -0.06
    ucher
    -0.06
    POSITIVE LOGITS
     spent
    0.07
    spent
    0.06
     time
    0.06
     Spend
    0.06
     spend
    0.06
     lav
    0.06
    yre
    0.06
     spends
    0.06
    nop
    0.06
     effort
    0.06
    Activations Density 0.017%

    No Known Activations