© 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. 82250
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and events

    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
    stral
    -0.08
    addir
    -0.08
    åĪļæīį
    -0.07
    endale
    -0.07
    åįĪ
    -0.07
    crast
    -0.07
     RootState
    -0.07
    antine
    -0.07
    hurst
    -0.07
    addtogroup
    -0.07
    POSITIVE LOGITS
     month
    0.09
     again
    0.07
     monthly
    0.07
     Month
    0.07
     year
    0.06
     became
    0.06
     Monthly
    0.06
    ingo
    0.06
    otos
    0.06
    lei
    0.06
    Activations Density 0.001%

    No Known Activations